API tools faq
paste
Guest User

Untitled

a guest
Oct 25th, 2017
1,506
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 139.02 KB | None | 0 0
raw download clone embed print report
  1. <!DOCTYPE html>
  2. <html>
  3. <head>
  4. <!--Import Google Icon Font-->
  5. <link href="https://fonts.googleapis.com/icon?family=Material+Icons" rel="stylesheet">
  6. <!--Import materialize.css-->
  7. <link type="text/css" rel="stylesheet" href="/static/materialize/css/materialize.min.css" media="screen,projection"/>
  8. <link type="text/css" rel="stylesheet" href="/static/style.css"/>
  9. <!--Let browser know website is optimized for mobile-->
  10. <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
  11.  
  12. </head>
  13. <body>
  14. <nav class="light-blue lighten-1" role="navigation">
  15. <div class="nav-wrapper container">
  16.  
  17. <form action="/search" method="get">
  18. <input id="query" placeholder="Type your query here..." type="text" name="q" class="validate" style="background-color: white; color: black; padding-left: 30px; margin-left: 10px; padding-right: 30px; margin-right: 10px; width: 78%" value="Michael Ii">
  19. <label for="query"></label>
  20. <input type="submit" value="Search" class="btn grey darken-1" style=" width: 10%; height: 45px; color: white;">
  21. </form>
  22.  
  23.  
  24. </div>
  25. </nav>
  26. <div class="container">
  27.  
  28. <div class="section">
  29. <!-- Icon Section -->
  30. <div class="row">
  31. <div class="col s12 m12">
  32. <div class="author-suggestions">
  33.  
  34.  
  35. </div>
  36.  
  37. <ul class="collapsible" data-collapsible="accordion">
  38. <li>
  39. <div class="collapsible-header"><i class="material-icons">build</i>Show debug output</div>
  40. <div class="collapsible-body">
  41. <pre class="debug-content">0.00001026: Started
  42. 0.00001582: Searching author for Michael Ii
  43. 0.13689957: Retrieved results from remote
  44. 0.14071447: Scanned 100 entries
  45. 0.14072516: Checking for authors
  46. 0.22594940: Found exact match
  47. 0.22597207: Building author subgraph for #2411
  48. 0.23599445: Found 29 related authors in graph
  49. Done in 0.236s</pre>
  50. </div>
  51. </li>
  52. </ul>
  53.  
  54.  
  55. <div class="card">
  56. <div class="card-content">
  57. <span class="card-title">Author <b>Michael Ii</b></span>
  58.  
  59. <svg width="1000" height="500"></svg>
  60.  
  61. <script src="https://d3js.org/d3.v4.min.js"></script>
  62. <script>
  63. var graph = {"center": "2411", "directed": false, "graph": {}, "links": [{"source": "427", "target": "424"}, {"source": "427", "target": "425"}, {"source": "427", "target": "426"}, {"source": "424", "target": "425"}, {"source": "424", "target": "426"}, {"source": "424", "target": "430"}, {"source": "424", "target": "621"}, {"source": "424", "target": "466"}, {"source": "424", "target": "556"}, {"source": "424", "target": "635"}, {"source": "424", "target": "7742"}, {"source": "424", "target": "2012"}, {"source": "424", "target": "2062"}, {"source": "424", "target": "2013"}, {"source": "424", "target": "865"}, {"source": "424", "target": "1869"}, {"source": "424", "target": "2079"}, {"source": "424", "target": "2003"}, {"source": "424", "target": "2216"}, {"source": "424", "target": "2217"}, {"source": "424", "target": "2218"}, {"source": "424", "target": "2151"}, {"source": "424", "target": "2411"}, {"source": "424", "target": "2499"}, {"source": "424", "target": "2500"}, {"source": "424", "target": "2594"}, {"source": "424", "target": "475"}, {"source": "424", "target": "2022"}, {"source": "424", "target": "2672"}, {"source": "425", "target": "426"}, {"source": "425", "target": "635"}, {"source": "426", "target": "2012"}, {"source": "426", "target": "2013"}, {"source": "426", "target": "865"}, {"source": "426", "target": "1869"}, {"source": "426", "target": "2079"}, {"source": "466", "target": "556"}, {"source": "475", "target": "2022"}, {"source": "865", "target": "1869"}, {"source": "865", "target": "1870"}, {"source": "865", "target": "2079"}, {"source": "1869", "target": "1870"}, {"source": "1869", "target": "2079"}, {"source": "1869", "target": "2411"}, {"source": "2012", "target": "2062"}, {"source": "2012", "target": "2013"}, {"source": "2003", "target": "2151"}, {"source": "2216", "target": "2217"}, {"source": "2216", "target": "2218"}, {"source": "2217", "target": "2218"}, {"source": "2499", "target": "2500"}], "multigraph": false, "nodes": [{"degree": 3, "id": "427", "name": "David Warland"}, {"degree": 27, "id": "424", "name": "William Bialek"}, {"degree": 7, "id": "425", "name": "Fred Rieke"}, {"degree": 8, "id": "426", "name": "Robert R. de Ruyter van Steveninck"}, {"degree": 1, "id": "430", "name": "Michael C. Crair"}, {"degree": 9, "id": "466", "name": "Daniel L. Ruderman"}, {"degree": 1, "id": "621", "name": "Leonid Kruglyak"}, {"degree": 2, "id": "556", "name": "A. Zee"}, {"degree": 2, "id": "635", "name": "W. Geoffrey Owen"}, {"degree": 16, "id": "475", "name": "L?on Bottou"}, {"degree": 1, "id": "7742", "name": "Rob de Ruyter van Steveninck"}, {"degree": 37, "id": "865", "name": "Naftali Tishby"}, {"degree": 6, "id": "1869", "name": "Elad Schneidman"}, {"degree": 2, "id": "1870", "name": "Idan Segev"}, {"degree": 4, "id": "2012", "name": "Adrienne L. Fairhall"}, {"degree": 2, "id": "2062", "name": "Blaise Ag?era y Arcas"}, {"degree": 3, "id": "2013", "name": "Geoffrey D. Lewen"}, {"degree": 4, "id": "2079", "name": "Naama Brenner"}, {"degree": 2, "id": "2003", "name": "Ilya Nemenman"}, {"degree": 5, "id": "2022", "name": "Susanne Still"}, {"degree": 3, "id": "2216", "name": "B. D. Wright"}, {"degree": 3, "id": "2217", "name": "Kamal Sen"}, {"degree": 3, "id": "2218", "name": "A. J. Doupe"}, {"degree": 2, "id": "2151", "name": "F. Shafee"}, {"degree": 2, "id": "2411", "name": "Michael Ii"}, {"degree": 2, "id": "2499", "name": "Tatyana Sharpee"}, {"degree": 2, "id": "2500", "name": "Nicole C. Rust"}, {"degree": 1, "id": "2594", "name": "Denis V. Chigirev"}, {"degree": 1, "id": "2672", "name": "Gurinder S. Atwal"}]};
  64. var svg = d3.select("svg"),
  65. width = +svg.attr("width"),
  66. height = +svg.attr("height");
  67.  
  68. var color = d3.scaleOrdinal(d3.schemeCategory20);
  69.  
  70. var simulation = d3.forceSimulation()
  71. .force("link", d3.forceLink().id(function(d) { return d.id; }))
  72. .force("charge", d3.forceManyBody().strength(function(d) {return -getNodeRadius(d) * 10}).distanceMax(100))
  73. .force("collide", d3.forceCollide().radius(getNodeRadius))
  74. .force("center", d3.forceCenter(width / 2, height / 2));
  75.  
  76. var link = svg.append("g")
  77. .attr("class", "links")
  78. .selectAll("line")
  79. .data(graph.links)
  80. .enter().append("line")
  81. .attr("stroke-width", function(d) { return d.key+1; });
  82.  
  83. var node = svg.append("g")
  84. .attr("class", "nodes")
  85. .selectAll("circle")
  86. .data(graph.nodes)
  87. .enter().append("circle")
  88. .attr("class", function(d) { return (d.id==graph.center) ? "center" : ""})
  89. .attr("r", getNodeRadius)
  90. .attr("fill", function(d) { return color(d.group); })
  91. .call(d3.drag()
  92. .on("start", dragstarted)
  93. .on("drag", dragged)
  94. .on("end", dragended));
  95.  
  96. function getNodeRadius(d) {
  97. return (Math.log(d.degree) + 1) * 2;
  98. }
  99.  
  100. node.append("title")
  101. .text(function(d) { return d.name; });
  102.  
  103. simulation
  104. .nodes(graph.nodes)
  105. .on("tick", ticked);
  106.  
  107. simulation.force("link")
  108. .links(graph.links);
  109.  
  110. function ticked() {
  111. link
  112. .attr("x1", function(d) { return d.source.x; })
  113. .attr("y1", function(d) { return d.source.y; })
  114. .attr("x2", function(d) { return d.target.x; })
  115. .attr("y2", function(d) { return d.target.y; });
  116.  
  117. node
  118. .attr("cx", function(d) { return d.x;})
  119. .attr("cy", function(d) { return d.y;});
  120. }
  121.  
  122. function dragstarted(d) {
  123. if (!d3.event.active) {
  124. simulation.alphaTarget(0.3).restart()
  125. }
  126. d.fx = d.x;
  127. d.fy = d.y;
  128. }
  129.  
  130. function dragged(d) {
  131. d.fx = d3.event.x;
  132. d.fy = d3.event.y;
  133. }
  134.  
  135. function dragended(d) {
  136. if (!d3.event.active) {
  137. simulation.alphaTarget(0)
  138. }
  139. d.fx = null;
  140. d.fy = null;
  141. }
  142. </script>
  143.  
  144.  
  145. </div>
  146. </div>
  147.  
  148.  
  149. <p>Found 100 results.</p>
  150.  
  151. <div class="result-row">
  152. <h5 style="width: 80%;"><strong id="result_index">1</strong> Computational Structure of coordinate transformations: A generalization study</h5>
  153. <p style="float: right; margin-top: -40px; color: lightgray;">0.14163247</p>
  154. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Zoubin Ghahramani%22">Zoubin Ghahramani</a>, <a href="/search?q=authors:%22Daniel M. Wolpert%22">Daniel M. Wolpert</a></h6>
  155. <p class="light">Computational structure of coordinate transformations: A generalization study Zoubin Ghahramani zoubin@psyche.mit.edu Daniel M. Wolpert wolpert@psyche.mit.edu <strong>Michael</strong> I. Jordan jordan@psyche.mit.edu Department of Brain &amp; Cognitive Sciences Massachusetts Institute of Technology Cambridge, MA 02139 Abstract One of the fundamental properties that both neural networks and the central nervous system share is ...</p>
  156. <div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div>
  157. </div>
  158.  
  159. <div class="result-row">
  160. <h5 style="width: 80%;"><strong id="result_index">2</strong> Reinforcement Learning with Soft State Aggregation</h5>
  161. <p style="float: right; margin-top: -40px; color: lightgray;">0.14094986</p>
  162. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Satinder P. Singh%22">Satinder P. Singh</a>, <a href="/search?q=authors:%22Tommi Jaakkola%22">Tommi Jaakkola</a></h6>
  163. <p class="light">Reinforcement Learning with Soft State Aggregation Satinder P. Singh singh@psyche.mit.edu Tommi Jaakkola tommi@psyche.mit.edu <strong>Michael</strong> I. Jordan jordan@psyche.mit.edu Dept. of Brain &amp; Cognitive Sciences (E-lO) M.I.T. Cambridge, MA 02139 Abstract It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learnin...</p>
  164. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div>
  165. </div>
  166.  
  167. <div class="result-row">
  168. <h5 style="width: 80%;"><strong id="result_index">3</strong> Forward dynamic models in human motor control: Psychophysical evidence</h5>
  169. <p style="float: right; margin-top: -40px; color: lightgray;">0.13598186</p>
  170. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Zoubin Ghahramani%22">Zoubin Ghahramani</a>, <a href="/search?q=authors:%22Daniel M. Wolpert%22">Daniel M. Wolpert</a></h6>
  171. <p class="light">Forward dynamic models in human motor control: Psychophysical evidence Daniel M. Wolpert wolpert@psyche .mit .edu Zouhin Ghahramani zoubin@psyche.mit.edu <strong>Michael</strong> I. Jordan jordan@psyche.mit.edu Department of Brain &amp; Cognitive Sciences Massachusetts Institute of Technology Cambridge, MA 02139 Abstract Based on computational principles, with as yet no direct experimental validation, it has been propos...</p>
  172. <div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  173. </div>
  174.  
  175. <div class="result-row">
  176. <h5 style="width: 80%;"><strong id="result_index">4</strong> Using a neural net to instantiate a deformable model</h5>
  177. <p style="float: right; margin-top: -40px; color: lightgray;">0.12931687</p>
  178. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Geoffrey E. Hinton%22">Geoffrey E. Hinton</a>, <a href="/search?q=authors:%22Christopher K. I. Williams%22">Christopher K. I. Williams</a>, <a href="/search?q=authors:%22Michael Revow%22">Michael Revow</a></h6>
  179. <p class="light">U sing a neural net to instantiate a deformable model Christopher K. I. Williams; <strong>Michael</strong> D. Revowand Geoffrey E. Hinton Department of Computer Science, University of Toronto Toronto, Ontario, Canada M5S lA4 Abstract Deformable models are an attractive approach to recognizing nonrigid objects which have considerable within class ...</p>
  180. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  181. </div>
  182.  
  183. <div class="result-row">
  184. <h5 style="width: 80%;"><strong id="result_index">5</strong> Boltzmann Chains and Hidden Markov Models</h5>
  185. <p style="float: right; margin-top: -40px; color: lightgray;">0.12844378</p>
  186. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Lawrence K. Saul%22">Lawrence K. Saul</a></h6>
  187. <p class="light">Boltzmann Chains and Hidden Markov Models Lawrence K. Saul and <strong>Michael</strong> I. Jordan lksaulOpsyche.mit.edu, jordanOpsyche.mit.edu Center for Biological and Computational Learning Massachusetts Institute of Technology 79 Amherst Street, E10-243 Cambridge, MA 02139 Abstract We propose a statistical mechanical framewo...</p>
  188. <div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%221%22">Topic 1 &lt;sequence speech model...&gt;</a></div>
  189. </div>
  190.  
  191. <div class="result-row">
  192. <h5 style="width: 80%;"><strong id="result_index">6</strong> Active Learning with Statistical Models</h5>
  193. <p style="float: right; margin-top: -40px; color: lightgray;">0.12777732</p>
  194. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22David A. Cohn%22">David A. Cohn</a>, <a href="/search?q=authors:%22Zoubin Ghahramani%22">Zoubin Ghahramani</a></h6>
  195. <p class="light">Active Learning with Statistical Models David A. Cohn, Zoubin Ghahramani, and <strong>Michael</strong> I. Jordan cohnQpsyche.mit.edu. zoubinQpsyche.mit.edu. jordan~syche.mit.edu Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge, MA 02139 Abstract For many types of learners one can compute the statistic...</p>
  196. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div>
  197. </div>
  198.  
  199. <div class="result-row">
  200. <h5 style="width: 80%;"><strong id="result_index">7</strong> Recognizing Handwritten Digits Using Mixtures of Linear Models</h5>
  201. <p style="float: right; margin-top: -40px; color: lightgray;">0.12614006</p>
  202. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Geoffrey E. Hinton%22">Geoffrey E. Hinton</a>, <a href="/search?q=authors:%22Peter Dayan%22">Peter Dayan</a>, <a href="/search?q=authors:%22Michael Revow%22">Michael Revow</a></h6>
  203. <p class="light">Recognizing Handwritten Digits Using Mixtures of Linear Models Geoffrey E Hinton <strong>Michael</strong> Revow Peter Dayan Deparbnent of Computer Science, University of Toronto Toronto, Ontario, Canada M5S lA4 Abstract We construct a mixture of locally linear generative models of a collection of pixel-based images of digits, and use them for re...</p>
  204. <div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  205. </div>
  206.  
  207. <div class="result-row">
  208. <h5 style="width: 80%;"><strong id="result_index">8</strong> Inferring Ground Truth from Subjective Labelling of Venus Images</h5>
  209. <p style="float: right; margin-top: -40px; color: lightgray;">0.12611838</p>
  210. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Pierre Baldi%22">Pierre Baldi</a>, <a href="/search?q=authors:%22Padhraic Smyth%22">Padhraic Smyth</a>, <a href="/search?q=authors:%22Usama M. Fayyad%22">Usama M. Fayyad</a>, <a href="/search?q=authors:%22Michael C. Burl%22">Michael C. Burl</a>, <a href="/search?q=authors:%22Pietro Perona%22">Pietro Perona</a></h6>
  211. <p class="light">Inferring Ground Truth from Subjective Labelling of Venus Images Padhraic Smyth, Usama Fayyad Jet Propulsion Laboratory 525-3660, Caltech, 4800 Oak Grove Drive, Pasadena, CA 91109 <strong>Michael</strong> Burl, Pietro Perona Department of Electrical Engineering Caltech, MS 116-81, Pasadena, CA 91125 Pierre Baldi* Jet Propulsion Laboratory 303-310, Caltech, 4800 Oak Grove Drive, Pasadena, CA 91109 Abstract In remote sensing applications &#x27;grou...</p>
  212. <div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  213. </div>
  214.  
  215. <div class="result-row">
  216. <h5 style="width: 80%;"><strong id="result_index">9</strong> On the Computational Utility of Consciousness</h5>
  217. <p style="float: right; margin-top: -40px; color: lightgray;">0.12184741</p>
  218. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael C. Mozer%22">Michael C. Mozer</a>, <a href="/search?q=authors:%22Donald W. Mathis%22">Donald W. Mathis</a></h6>
  219. <p class="light">On the Computational Utility of Consciousness Donald W. Mathis and <strong>Michael</strong> C. Mozer mathis@cs.colorado.edu, mozer@cs.colorado.edu Department of Computer Science and Institute of Cognitive Science University of Colorado, Boulder Boulder, CO 80309-0430 Abstract We propose a computational framework for understanding a...</p>
  220. <div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  221. </div>
  222.  
  223. <div class="result-row">
  224. <h5 style="width: 80%;"><strong id="result_index">10</strong> Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task</h5>
  225. <p style="float: right; margin-top: -40px; color: lightgray;">0.12040052</p>
  226. <h6><strong id="year">2000</strong> - <a href="/search?q=authors:%22Geoffrey E. Hinton%22">Geoffrey E. Hinton</a>, <a href="/search?q=authors:%22Brian Sallans%22">Brian Sallans</a></h6>
  227. <p class="light">...ics, 13:835846, 1983. [3] R. S. Sutton. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proc. International Conference on Machine Learning, 1990. [4] Tommi Jaakkola, Satinder P. Singh, and <strong>Michael</strong> 1. Jordan. Reinforcement learning algorithm for partially observable Markov decision problems. In Gerald Tesauro, David S. Touretzky, and Todd K. Leen, editors, Advances in Neural Information Processing Systems, volume 7, pages 345-352. The M...</p>
  228. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  229. </div>
  230.  
  231. <div class="result-row">
  232. <h5 style="width: 80%;"><strong id="result_index">11</strong> The Ni1000: High Speed Parallel VLSI for Implementing Multilayer Perceptrons</h5>
  233. <p style="float: right; margin-top: -40px; color: lightgray;">0.11573849</p>
  234. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael P. Perrone%22">Michael P. Perrone</a>, <a href="/search?q=authors:%22Leon N. Cooper%22">Leon N. Cooper</a></h6>
  235. <p class="light">The NilOOO: High Speed Parallel VLSI for Implementing Multilayer Perceptrons <strong>Michael</strong> P. Perrone Thomas J. Watson Research Center P.O. Box 704 Yorktown Heights, NY 10598 mppGwatson.ibm.com Leon N Cooper Institute for Brain and Neural Systems Brown University Providence, Ri 02912 IncGcns.brown.edu Abstract In this paper we pr...</p>
  236. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div>
  237. </div>
  238.  
  239. <div class="result-row">
  240. <h5 style="width: 80%;"><strong id="result_index">12</strong> Monte Carlo Sampling for Regret Minimization in Extensive Games</h5>
  241. <p style="float: right; margin-top: -40px; color: lightgray;">0.11249081</p>
  242. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Michael Bowling%22">Michael Bowling</a>, <a href="/search?q=authors:%22Martin Zinkevich%22">Martin Zinkevich</a>, <a href="/search?q=authors:%22Kevin Waugh%22">Kevin Waugh</a>, <a href="/search?q=authors:%22Marc Lanctot%22">Marc Lanctot</a></h6>
  243. <p class="light">...ersity Pittsburgh PA 15213-3891 waugh@cs.cmu.edu Marc Lanctot Department of Computing Science University of Alberta Edmonton, Alberta, Canada T6G 2E8 lanctot@ualberta.ca Martin Zinkevich Yahoo! Research Santa Clara, CA, USA 95054 maz@yahoo-inc.com <strong>Michael</strong> Bowling Department of Computing Science University of Alberta Edmonton, Alberta, Canada T6G 2E8 bowling@cs.ualberta.ca Abstract Sequential decision-making with multiple agents and imperfect information is commonly modeled as an extensive gam...</p>
  244. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  245. </div>
  246.  
  247. <div class="result-row">
  248. <h5 style="width: 80%;"><strong id="result_index">13</strong> Strategy Grafting in Extensive Games</h5>
  249. <p style="float: right; margin-top: -40px; color: lightgray;">0.11197392</p>
  250. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Michael Bowling%22">Michael Bowling</a>, <a href="/search?q=authors:%22Kevin Waugh%22">Kevin Waugh</a>, <a href="/search?q=authors:%22Nolan Bard%22">Nolan Bard</a></h6>
  251. <p class="light">Strategy Grafting in Extensive Games Kevin Waugh waugh@cs.cmu.edu Department of Computer Science Carnegie Mellon University Nolan Bard, <strong>Michael</strong> Bowling {nolan,bowling}@cs.ualberta.ca Department of Computing Science University of Alberta Abstract Extensive games are often used to model the interactions of multiple agents within an environment. Much recent work has focused on increasi...</p>
  252. <div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  253. </div>
  254.  
  255. <div class="result-row">
  256. <h5 style="width: 80%;"><strong id="result_index">14</strong> Reinforcement Learning Methods for Continuous-Time Markov Decision Problems</h5>
  257. <p style="float: right; margin-top: -40px; color: lightgray;">0.110282324</p>
  258. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Steven J. Bradtke%22">Steven J. Bradtke</a>, <a href="/search?q=authors:%22Michael O. Duff%22">Michael O. Duff</a></h6>
  259. <p class="light">Reinforcement Learning Methods for Continuous-Time Markov Decision Problems Steven J. Bradtke Computer Science Department University of Massachusetts Amherst, MA 01003 bradtkeGcs.umass.edu <strong>Michael</strong> O. Duff Computer Science Department University of Massachusetts Amherst, MA 01003 duffGcs.umass.edu Abstract Semi-Markov Decision Problems are continuous time generalizations of discrete time Markov Decision Problems. A number of reinforceme...</p>
  260. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  261. </div>
  262.  
  263. <div class="result-row">
  264. <h5 style="width: 80%;"><strong id="result_index">15</strong> A model of the hippocampus combining self-organization and associative memory function</h5>
  265. <p style="float: right; margin-top: -40px; color: lightgray;">0.106623605</p>
  266. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael E. Hasselmo%22">Michael E. Hasselmo</a>, <a href="/search?q=authors:%22Eric Schnell%22">Eric Schnell</a>, <a href="/search?q=authors:%22Joshua Berke%22">Joshua Berke</a>, <a href="/search?q=authors:%22Edi Barkai%22">Edi Barkai</a></h6>
  267. <p class="light">A model of the hippocampus combining selforganization and associative memory function. <strong>Michael</strong> E. Hasselmo, Eric Schnell Joshua Berke and Edi Barkai Dept. of Psychology, Harvard University 33 Kirkland St., Cambridge, MA 02138 hasselmo@katla.harvard.edu Abstract A model of the hippocampus is presented which forms rapid self-organized ...</p>
  268. <div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2218%22">Topic 18 &lt;neuron spike time input...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div>
  269. </div>
  270.  
  271. <div class="result-row">
  272. <h5 style="width: 80%;"><strong id="result_index">16</strong> Regret-Based Pruning in Extensive-Form Games</h5>
  273. <p style="float: right; margin-top: -40px; color: lightgray;">0.10455509</p>
  274. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Tuomas Sandholm%22">Tuomas Sandholm</a>, <a href="/search?q=authors:%22Noam Brown%22">Noam Brown</a></h6>
  275. <p class="light">...al. 6.1 Acknowledgement This material is based on work supported by the National Science Foundation under grants IIS1320620 and IIS-1546752, as well as XSEDE computing resources provided by the Pittsburgh Supercomputing Center. 8 References [1] <strong>Michael</strong> Bowling, Neil Burch, <strong>Michael</strong> Johanson, and Oskari Tammelin. Heads-up limit holdem poker is solved. Science, 347(6218):145?149, 2015. [2] Noam Brown, Sam Ganzfried, and Tuomas Sandholm. Hierarchical abstraction, distributed equilibrium computa...</p>
  276. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div>
  277. </div>
  278.  
  279. <div class="result-row">
  280. <h5 style="width: 80%;"><strong id="result_index">17</strong> Convergence and No-Regret in Multiagent Learning</h5>
  281. <p style="float: right; margin-top: -40px; color: lightgray;">0.10080891</p>
  282. <h6><strong id="year">2004</strong> - <a href="/search?q=authors:%22Michael Bowling%22">Michael Bowling</a></h6>
  283. <p class="light">Convergence and No-Regret in Multiagent Learning <strong>Michael</strong> Bowling Department of Computing Science University of Alberta Edmonton, Alberta Canada T6G 2E8 bowling@cs.ualberta.ca Abstract Learning in a multiagent system is a challenging problem due to two key factors. First, if other agents are simult...</p>
  284. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  285. </div>
  286.  
  287. <div class="result-row">
  288. <h5 style="width: 80%;"><strong id="result_index">18</strong> Boosting the Performance of RBF Networks with Dynamic Decay Adjustment</h5>
  289. <p style="float: right; margin-top: -40px; color: lightgray;">0.100016266</p>
  290. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Michael R. Berthold%22">Michael R. Berthold</a>, <a href="/search?q=authors:%22Jay Diamond%22">Jay Diamond</a></h6>
  291. <p class="light">Boosting the Performance of RBF Networks with Dynamic Decay Adjustment <strong>Michael</strong> R. Berthold Forschungszentrum Informatik Gruppe ACID (Prof. D. Schmid) Haid-und-Neu-Strasse 10-14 76131 Karlsruhe, Germany eMail: berthold@fzLde Jay Diamond Intel Corporation 2200 Mission College Blvd. Santa Clara, CA, USA 95052 MS:SC9-15 eM...</p>
  292. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  293. </div>
  294.  
  295. <div class="result-row">
  296. <h5 style="width: 80%;"><strong id="result_index">19</strong> Tractable Objectives for Robust Policy Optimization</h5>
  297. <p style="float: right; margin-top: -40px; color: lightgray;">0.098560356</p>
  298. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Michael Bowling%22">Michael Bowling</a>, <a href="/search?q=authors:%22Katherine Chen%22">Katherine Chen</a></h6>
  299. <p class="light">Tractable Objectives for Robust Policy Optimization Katherine Chen University of Alberta <strong>Michael</strong> Bowling University of Alberta kchen4@ualberta.ca bowling@cs.ualberta.ca Abstract Robust policy optimization acknowledges that risk-aversion plays a vital role in real-world decision-making. When faced with uncertainty about the effects of ...</p>
  300. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  301. </div>
  302.  
  303. <div class="result-row">
  304. <h5 style="width: 80%;"><strong id="result_index">20</strong> Approximate Inference A lgorithms for Two-Layer Bayesian Networks</h5>
  305. <p style="float: right; margin-top: -40px; color: lightgray;">0.095917046</p>
  306. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Andrew Y. Ng%22">Andrew Y. Ng</a></h6>
  307. <p class="light">Approximate inference algorithms for two-layer Bayesian networks AndrewY. Ng Computer Science Division UC Berkeley Berkeley, CA 94720 ang@cs.berkeley.edu <strong>Michael</strong> I. Jordan Computer Science Division and Department of Statistics UC Berkeley Berkeley, CA 94720 jordan@cs.berkeley.edu Abstract We present a class of approximate inference algorithms for graphical models of the QMR-DT type. We give convergen...</p>
  308. <div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  309. </div>
  310.  
  311. <div class="result-row">
  312. <h5 style="width: 80%;"><strong id="result_index">21</strong> Fast Randomized Kernel Ridge Regression with Statistical Guarantees</h5>
  313. <p style="float: right; margin-top: -40px; color: lightgray;">0.09449927</p>
  314. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Michael W. Mahoney%22">Michael W. Mahoney</a>, <a href="/search?q=authors:%22Ahmed Alaoui%22">Ahmed Alaoui</a></h6>
  315. <p class="light">Fast Randomized Kernel Ridge Regression with Statistical Guarantees? Ahmed El Alaoui ? <strong>Michael</strong> W. Mahoney ? ? Electrical Engineering and Computer Sciences ? Statistics and International Computer Science Institute University of California, Berkeley, Berkeley, CA 94720. {elalaoui@eecs,mmahoney@stat}.berkeley.edu Abstract One approach to...</p>
  316. <div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  317. </div>
  318.  
  319. <div class="result-row">
  320. <h5 style="width: 80%;"><strong id="result_index">22</strong> A dynamical model of priming and repetition blindness</h5>
  321. <p style="float: right; margin-top: -40px; color: lightgray;">0.094178244</p>
  322. <h6><strong id="year">1992</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Daphne Bavelier%22">Daphne Bavelier</a></h6>
  323. <p class="light">A dynamical model of priming and repetition blindness Daphne Bavelier Laboratory of Neuropsychology The Salk Institute La J oHa, CA 92037 <strong>Michael</strong> I. Jordan Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA 02139 Abstract We describe a model of visual word recognition that accounts for several aspects of the temporal processing of sequences o...</p>
  324. <div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div><div class="chip"><a href="/search?q=topic:%221%22">Topic 1 &lt;sequence speech model...&gt;</a></div>
  325. </div>
  326.  
  327. <div class="result-row">
  328. <h5 style="width: 80%;"><strong id="result_index">23</strong> Online Regret Bounds for Undiscounted Continuous Reinforcement Learning</h5>
  329. <p style="float: right; margin-top: -40px; color: lightgray;">0.09214892</p>
  330. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Ronald Ortner%22">Ronald Ortner</a>, <a href="/search?q=authors:%22Daniil Ryabko%22">Daniil Ryabko</a></h6>
  331. <p class="light">...I 2009, pages 25?42, 2009. [6] Andrey Bernstein and Nahum Shimkin. Adaptive-resolution reinforcement learning with polynomial exploration in deterministic domains. Mach. Learn., 81(3):359?397, 2010. [7] Emma Brunskill, Bethany R. Leffler, Lihong Li, <strong>Michael</strong> L. Littman, and Nicholas Roy. Provably efficient learning with typed parametric models. J. Mach. Learn. Res., 10:1955?1988, 2009. [8] S?ebastien Bubeck, R?emi Munos, Gilles Stoltz, and Csaba Szepesv?ari. Online optimization of ?-armed bandits...</p>
  332. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  333. </div>
  334.  
  335. <div class="result-row">
  336. <h5 style="width: 80%;"><strong id="result_index">24</strong> Query-Aware MCMC</h5>
  337. <p style="float: right; margin-top: -40px; color: lightgray;">0.09214892</p>
  338. <h6><strong id="year">2011</strong> - <a href="/search?q=authors:%22Andrew McCallum%22">Andrew McCallum</a>, <a href="/search?q=authors:%22Michael L. Wick%22">Michael L. Wick</a></h6>
  339. <p class="light">Query-Aware MCMC Andrew McCallum Department of Computer Science University of Massachusetts Amherst, MA mccallum@cs.umass.edu <strong>Michael</strong> Wick Department of Computer Science University of Massachusetts Amherst, MA mwick@cs.umass.edu Abstract Traditional approaches to probabilistic inference such as loopy belief propagation and Gibbs sampling typically compute marginals for all...</p>
  340. <div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div>
  341. </div>
  342.  
  343. <div class="result-row">
  344. <h5 style="width: 80%;"><strong id="result_index">25</strong> Hierarchical Image Probability (H1P) Models</h5>
  345. <p style="float: right; margin-top: -40px; color: lightgray;">0.09104716</p>
  346. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22Clay Spence%22">Clay Spence</a>, <a href="/search?q=authors:%22Lucas C. Parra%22">Lucas C. Parra</a></h6>
  347. <p class="light">...using Gaussian Markov random fields. IEEE Trans. ASSP, 33:959-963, 1985 . [5] Stuart Geman and Donald Geman. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. PAMI, PAMI-6(6):194-207 , November 1984. [6] <strong>Michael</strong> 1. Jordan, editor. Learning in Graphical Models, volume 89 of NATO Science Series D: Behavioral and Brain Sciences. Kluwer Academic, 1998. [7] Mark R. Luettgen and Alan S. Will sky. Likelihood calculation for a class of multiscale stochastic ...</p>
  348. <div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div>
  349. </div>
  350.  
  351. <div class="result-row">
  352. <h5 style="width: 80%;"><strong id="result_index">26</strong> Approximate Inference and Protein-Folding</h5>
  353. <p style="float: right; margin-top: -40px; color: lightgray;">0.09100095</p>
  354. <h6><strong id="year">2002</strong> - <a href="/search?q=authors:%22Yair Weiss%22">Yair Weiss</a>, <a href="/search?q=authors:%22Chen Yanover%22">Chen Yanover</a></h6>
  355. <p class="light">... direction for future research is to try and learn the energy function from examples. Inference algorithms such as BP may play an important role in the learning procedure. References [1] R. Cowell. Introduction to inference in Bayesian networks. In <strong>Michael</strong> I. Jordan, editor, Learning in Graphical Models. Morgan Kauffmann , 1998. [2] Johan Desmet , Marc De Maeyer, Bart Hazes, and Ignace Lasters . The dead-end elmination theorem and its use in protein side-chain positioning. Nature, 356:539542, 1...</p>
  356. <div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div>
  357. </div>
  358.  
  359. <div class="result-row">
  360. <h5 style="width: 80%;"><strong id="result_index">27</strong> Sub-sampled Newton Methods with Non-uniform Sampling</h5>
  361. <p style="float: right; margin-top: -40px; color: lightgray;">0.09003641</p>
  362. <h6><strong id="year">2016</strong> - <a href="/search?q=authors:%22Peng Xu%22">Peng Xu</a>, <a href="/search?q=authors:%22Michael W. Mahoney%22">Michael W. Mahoney</a>, <a href="/search?q=authors:%22Christopher R?%22">Christopher R?</a>, <a href="/search?q=authors:%22Jiyan Yang%22">Jiyan Yang</a>, <a href="/search?q=authors:%22Farbod Roosta-Khorasani%22">Farbod Roosta-Khorasani</a></h6>
  363. <p class="light">Sub-sampled Newton Methods with Non-uniform Sampling Peng Xu? Jiyan Yang? Farbod Roosta-Khorasani? Christopher R?? <strong>Michael</strong> W. Mahoney? ? Stanford University ? University of California at Berkeley pengxu@stanford.edu jiyan@stanford.edu farbod@icsi.berkeley.edu chrismre@cs.stanford.edu mmahoney@stat.berkeley.edu Abstract We consider the problemP of finding the min...</p>
  364. <div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  365. </div>
  366.  
  367. <div class="result-row">
  368. <h5 style="width: 80%;"><strong id="result_index">28</strong> Efficient Monte Carlo Counterfactual Regret Minimization in Games with Many Player Actions</h5>
  369. <p style="float: right; margin-top: -40px; color: lightgray;">0.0899196</p>
  370. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Marc Lanctot%22">Marc Lanctot</a>, <a href="/search?q=authors:%22Richard G. Gibson%22">Richard G. Gibson</a>, <a href="/search?q=authors:%22Duane Szafron%22">Duane Szafron</a>, <a href="/search?q=authors:%22Neil Burch%22">Neil Burch</a></h6>
  371. <p class="light">...rfactual regret minimization to create competitive multiplayer poker agents. In Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 159?166, 2010. [2] Richard Gibson, Marc Lanctot, Neil Burch, Duane Szafron, and <strong>Michael</strong> Bowling. Generalized sampling and variance in counterfactual regret minimization. In Twenty-Sixth Conference on Artificial Intelligence (AAAI), pages 1355?1361, 2012. [3] Richard Gibson and Duane Szafron. On strategy stitching in large extens...</p>
  372. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  373. </div>
  374.  
  375. <div class="result-row">
  376. <h5 style="width: 80%;"><strong id="result_index">29</strong> Feature-distributed sparse regression: a screen-and-clean approach</h5>
  377. <p style="float: right; margin-top: -40px; color: lightgray;">0.089451596</p>
  378. <h6><strong id="year">2016</strong> - <a href="/search?q=authors:%22Michael W. Mahoney%22">Michael W. Mahoney</a>, <a href="/search?q=authors:%22Yuekai Sun%22">Yuekai Sun</a>, <a href="/search?q=authors:%22Michael Saunders%22">Michael Saunders</a>, <a href="/search?q=authors:%22Jiyan Yang%22">Jiyan Yang</a></h6>
  379. <p class="light">Feature-distributed sparse regression: a screen-and-clean approach Jiyan Yang? <strong>Michael</strong> W. Mahoney? <strong>Michael</strong> A. Saunders? Yuekai Sun? ? Stanford University ? University of California at Berkeley ? University of Michigan jiyan@stanford.edu mmahoney@stat.berkeley.edu saunders@stanford.edu yuekai@umich.edu Abstract Most existing ap...</p>
  380. <div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div>
  381. </div>
  382.  
  383. <div class="result-row">
  384. <h5 style="width: 80%;"><strong id="result_index">30</strong> Synergies in learning words and their referents</h5>
  385. <p style="float: right; margin-top: -40px; color: lightgray;">0.08907308</p>
  386. <h6><strong id="year">2010</strong> - <a href="/search?q=authors:%22Michael J. Black%22">Michael J. Black</a>, <a href="/search?q=authors:%22Mark Johnson%22">Mark Johnson</a>, <a href="/search?q=authors:%22Katherine Demuth%22">Katherine Demuth</a>, <a href="/search?q=authors:%22Bevan Jones%22">Bevan Jones</a></h6>
  387. <p class="light">...ies in learning words and their referents Katherine Demuth Department of Linguistics Macquarie University Sydney, NSW 2109 Katherine.Demuth@mq.edu.au Mark Johnson Department of Computing Macquarie University Sydney, NSW 2109 Mark.Johnson@mq.edu.au <strong>Michael</strong> Frank Department of Psychology Stanford University Palo Alto, CA 94305 mcfrank@mit.edu Bevan K. Jones School of Informatics University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB, UK B.K.Jones@sms.ed.ac.uk Abstract This paper present...</p>
  388. <div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div><div class="chip"><a href="/search?q=topic:%221%22">Topic 1 &lt;sequence speech model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div>
  389. </div>
  390.  
  391. <div class="result-row">
  392. <h5 style="width: 80%;"><strong id="result_index">31</strong> Direct memory access using two cues: Finding the intersection of sets in a connectionist model</h5>
  393. <p style="float: right; margin-top: -40px; color: lightgray;">0.088693365</p>
  394. <h6><strong id="year">1990</strong> - <a href="/search?q=authors:%22Janet Wiles%22">Janet Wiles</a>, <a href="/search?q=authors:%22Michael S. Humphreys%22">Michael S. Humphreys</a>, <a href="/search?q=authors:%22John D. Bain%22">John D. Bain</a>, <a href="/search?q=authors:%22Simon Dennis%22">Simon Dennis</a></h6>
  395. <p class="light">Direct memory access using two cues: Finding the intersection of sets in a connectionist model Janet Wiles, <strong>Michael</strong> S. Humphreys, John D. Bain and Simon Dennis Departments of Psychology and Computer Science University of Queensland QLD 4072 Australia email: janet@psych.psy.uq.oz.au Abstract For lack of alternative models, search and decision processes hav...</p>
  396. <div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  397. </div>
  398.  
  399. <div class="result-row">
  400. <h5 style="width: 80%;"><strong id="result_index">32</strong> Boosting with Multi-Way Branching in Decision Trees</h5>
  401. <p style="float: right; margin-top: -40px; color: lightgray;">0.08803334</p>
  402. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22Yishay Mansour%22">Yishay Mansour</a>, <a href="/search?q=authors:%22David A. McAllester%22">David A. McAllester</a></h6>
  403. <p class="light">...that I(T&#x27;)/IT&#x27;I ~ Wm which now yields WI ~ e(k)wm/k as desired. 0 References [1] Leo Breiman, Jerome H. Friedman, Richard A. Olshen, and Charles J. Stone. Classification and Regression Trees. Wadsworth International Group, 1984. [2] Tom Dietterich, <strong>Michael</strong> Kearns and Yishay Mansour. Applying the Weak Learning Framework to understand and improve C4.5. In Proc. of Machine Learning, 96-104, 1996. [3] Yoav Freund. Boosting a weak learning algorithm by majority. Information and Computation, 121(2):2...</p>
  404. <div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div>
  405. </div>
  406.  
  407. <div class="result-row">
  408. <h5 style="width: 80%;"><strong id="result_index">33</strong> Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models</h5>
  409. <p style="float: right; margin-top: -40px; color: lightgray;">0.08740865</p>
  410. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Michael C. Hughes%22">Michael C. Hughes</a>, <a href="/search?q=authors:%22Erik Sudderth%22">Erik Sudderth</a>, <a href="/search?q=authors:%22William T. Stephenson%22">William T. Stephenson</a></h6>
  411. <p class="light">Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models <strong>Michael</strong> C. Hughes, William Stephenson, and Erik B. Sudderth Department of Computer Science, Brown University, Providence, RI 02912 mhughes@cs.brown.edu, wtstephe@gmail.com, sudderth@cs.brown.edu Abstract Bayesian nonparametric hidden Markov models a...</p>
  412. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  413. </div>
  414.  
  415. <div class="result-row">
  416. <h5 style="width: 80%;"><strong id="result_index">34</strong> Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning</h5>
  417. <p style="float: right; margin-top: -40px; color: lightgray;">0.08649173</p>
  418. <h6><strong id="year">2006</strong> - <a href="/search?q=authors:%22Peter Auer%22">Peter Auer</a>, <a href="/search?q=authors:%22Ronald Ortner%22">Ronald Ortner</a></h6>
  419. <p class="light">...rk was supported in part by the the Austrian Science Fund FWF (S9104-N04 SP4) and the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002506778. This publication only reflects the authors? views. References [1] <strong>Michael</strong> J. Kearns and Satinder P. Singh. Near-optimal reinforcement learning in polynomial time. Mach. Learn., 49:209?232, 2002. [2] Ronen I. Brafman and Moshe Tennenholtz. R-max ? a general polynomial time algorithm for near-optimal reinforcement le...</p>
  420. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  421. </div>
  422.  
  423. <div class="result-row">
  424. <h5 style="width: 80%;"><strong id="result_index">35</strong> Learning Global Direct Inverse Kinematics</h5>
  425. <p style="float: right; margin-top: -40px; color: lightgray;">0.085179746</p>
  426. <h6><strong id="year">1991</strong> - <a href="/search?q=authors:%22David DeMers%22">David DeMers</a>, <a href="/search?q=authors:%22Kenneth Kreutz-Delgado%22">Kenneth Kreutz-Delgado</a></h6>
  427. <p class="light">...-Wesley. David DeMers &amp; Kenneth Kreutz-Delgado (1991), &#x27;Learning Global Topological Properties of Robot Kinematic Mappings for Neural Network-Based Configuration Control&#x27;, in Bekey, ed. Proc. USC Workshop on Neural Networks in Robotics, (to appear). <strong>Michael</strong> I. Jordan (1988), &#x27;Supervised Learning and Systems with Excess Degrees of Freedom&#x27;, COINS Technical Report 88-27, University of Massachusetts at Amherst. <strong>Michael</strong>!. Jordan &amp; David E. Rumelhart (1990), &#x27;Forward Models: Supervised Learning with ...</p>
  428. <div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div>
  429. </div>
  430.  
  431. <div class="result-row">
  432. <h5 style="width: 80%;"><strong id="result_index">36</strong> Exact Solutions to Time-Dependent MDPs</h5>
  433. <p style="float: right; margin-top: -40px; color: lightgray;">0.08317559</p>
  434. <h6><strong id="year">2000</strong> - <a href="/search?q=authors:%22Michael L. Littman%22">Michael L. Littman</a>, <a href="/search?q=authors:%22Justin A. Boyan%22">Justin A. Boyan</a></h6>
  435. <p class="light">Exact Solutions to Time-Dependent MDPs Justin A. Boyan? ITA Software Building 400 One Kendall Square Cambridge, MA 02139 jab@itasoftware.com <strong>Michael</strong> L. Littman AT&amp;T Labs-Research and Duke University 180 Park Ave. Room A275 Florham Park, NJ 07932-0971 USA mlittman@research.att. com Abstract We describe an extension of the Markov decision process model in which a continuous time dimension ...</p>
  436. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  437. </div>
  438.  
  439. <div class="result-row">
  440. <h5 style="width: 80%;"><strong id="result_index">37</strong> Computing Nash Equilibria in Generalized Interdependent Security Games</h5>
  441. <p style="float: right; margin-top: -40px; color: lightgray;">0.08270554</p>
  442. <h6><strong id="year">2014</strong> - <a href="/search?q=authors:%22Luis E. Ortiz%22">Luis E. Ortiz</a>, <a href="/search?q=authors:%22Hau Chan%22">Hau Chan</a></h6>
  443. <p class="light">...f interdependent information security games. ACM Comput. Surv., 47(2):23:1?23:38, August 2014. [6] W.W. Zachary. An information flow model for conflict and fission in small groups. Journal of Anthropological Research, 33:452?473, 1977. [7] Hau Chan, <strong>Michael</strong> Ceyko, and Luis E. Ortiz. Interdependent defense games: Modeling interdependent security under deliberate attacks. In Proceedings of the Conference on Uncertainty in Artificial Intelligence, UAI ?12, pages 152?162, 2012. [8] <strong>Michael</strong> Kearns an...</p>
  444. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  445. </div>
  446.  
  447. <div class="result-row">
  448. <h5 style="width: 80%;"><strong id="result_index">38</strong> Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference</h5>
  449. <p style="float: right; margin-top: -40px; color: lightgray;">0.082559235</p>
  450. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Andrew McCallum%22">Andrew McCallum</a>, <a href="/search?q=authors:%22Michael J. Black%22">Michael J. Black</a>, <a href="/search?q=authors:%22Khashayar Rohanimanesh%22">Khashayar Rohanimanesh</a>, <a href="/search?q=authors:%22Sameer Singh%22">Sameer Singh</a></h6>
  451. <p class="light">Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference <strong>Michael</strong> Wick, Khashayar Rohanimanesh, Sameer Singh, Andrew McCallum Department of Computer Science University of Massachusetts Amherst Amherst, MA 01003 {mwick,khash,sameer,mccallum}@cs.umass.edu Abstract Large, relational factor graphs with structu...</p>
  452. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  453. </div>
  454.  
  455. <div class="result-row">
  456. <h5 style="width: 80%;"><strong id="result_index">39</strong> Interior Point Implementations of Alternating Minimization Training</h5>
  457. <p style="float: right; margin-top: -40px; color: lightgray;">0.08187237</p>
  458. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22Peter T. Szymanski%22">Peter T. Szymanski</a>, <a href="/search?q=authors:%22Michael Lemmon%22">Michael Lemmon</a></h6>
  459. <p class="light">Interior Point Implementations of Alternating Minimization Training <strong>Michael</strong> Lemmon Dept . of Electrical Engineering University of Notre Dame Notre Dame, IN 46556 lemmon@maddog.ee.nd.edu Peter T. Szymanski Dept. of Electrical Engineering University of Notre Dame Notre Dame, IN 46556 pszymans@maddog.ee.nd.edu Abstrac...</p>
  460. <div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  461. </div>
  462.  
  463. <div class="result-row">
  464. <h5 style="width: 80%;"><strong id="result_index">40</strong> An MEG Study of Response Latency and Variability in the Human Visual System During a Visual-Motor Integration Task</h5>
  465. <p style="float: right; margin-top: -40px; color: lightgray;">0.081676245</p>
  466. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22Barak A. Pearlmutter%22">Barak A. Pearlmutter</a>, <a href="/search?q=authors:%22Akaysha C. Tang%22">Akaysha C. Tang</a>, <a href="/search?q=authors:%22Tim A. Hely%22">Tim A. Hely</a>, <a href="/search?q=authors:%22Michael Zibulevsky%22">Michael Zibulevsky</a>, <a href="/search?q=authors:%22Michael P. Weisend%22">Michael P. Weisend</a></h6>
  467. <p class="light">...gy University of New Mexico Albuquerque, NM 87131 akaysha@unm.edu Barak A. Pearlmutter Dept. of Computer Science University of New Mexico Albuquerque, NM 87131 bap@cs. unm. edu Tim A. Hely Santa Fe Institute 1399 Hyde Park Road Santa Fe, NM 87501 <strong>Michael</strong> Zibulevsky Dept. of Computer Science University of New Mexico Albuquerque, NM 87131 <strong>Michael</strong> P. Weisend VA Medical Center 1501 San Pedro SE Albuquerque, NM 87108 timhely@santafe. edu michael@cs.unm.edu mweisend@unm.edu Abstract Human reac...</p>
  468. <div class="chip"><a href="/search?q=topic:%2222%22">Topic 22 &lt;signal source circuit time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div>
  469. </div>
  470.  
  471. <div class="result-row">
  472. <h5 style="width: 80%;"><strong id="result_index">41</strong> Learning Multiple Tasks using Shared Hypotheses</h5>
  473. <p style="float: right; margin-top: -40px; color: lightgray;">0.08102868</p>
  474. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Yishay Mansour%22">Yishay Mansour</a>, <a href="/search?q=authors:%22Koby Crammer%22">Koby Crammer</a></h6>
  475. <p class="light">...riments. We also plan to derive theory and algorithms for soft association of tasks to classifiers. Acknowledgements: The research is partially supported by a grants from ISF, BSF and European Union grant IRG-256479. 8 References [1] Yonatan Amit, <strong>Michael</strong> Fink, Nathan Srebro, and Shimon Ullman. Uncovering shared structures in multiclass classification. In ICML, pages 17?24, 2007. [2] Rie Kubota Ando and Tong Zhang. A framework for learning predictive structures from multiple tasks and unlabele...</p>
  476. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  477. </div>
  478.  
  479. <div class="result-row">
  480. <h5 style="width: 80%;"><strong id="result_index">42</strong> Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain</h5>
  481. <p style="float: right; margin-top: -40px; color: lightgray;">0.08068131</p>
  482. <h6><strong id="year">2016</strong> - <a href="/search?q=authors:%22Oluwasanmi O. Koyejo%22">Oluwasanmi O. Koyejo</a>, <a href="/search?q=authors:%22Michael N. Jones%22">Michael N. Jones</a>, <a href="/search?q=authors:%22Timothy Rubin%22">Timothy Rubin</a>, <a href="/search?q=authors:%22Tal Yarkoni%22">Tal Yarkoni</a></h6>
  483. <p class="light">Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain Timothy N. Rubin SurveyMonkey Oluwasanmi Koyejo Univ. of Illinois, Urbana-Champaign <strong>Michael</strong> N. Jones Indiana University Tal Yarkoni University of Texas at Austin Abstract This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the Correspondence-LDA model that allows for variable spatial representations to...</p>
  484. <div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  485. </div>
  486.  
  487. <div class="result-row">
  488. <h5 style="width: 80%;"><strong id="result_index">43</strong> Approximating Semidefinite Programs in Sublinear Time</h5>
  489. <p style="float: right; margin-top: -40px; color: lightgray;">0.08042687</p>
  490. <h6><strong id="year">2011</strong> - <a href="/search?q=authors:%22Elad Hazan%22">Elad Hazan</a>, <a href="/search?q=authors:%22Dan Garber%22">Dan Garber</a></h6>
  491. <p class="light">...3?581, 2005. [4] Sanjeev Arora, James R. Lee, and Assaf Naor. Euclidean distortion and the sparsest cut. In Proceedings of the thirty-seventh annual ACM symposium on Theory of computing, STOC ?05, pages 553?562, 2005. [5] Eric P. Xing, Andrew Y. Ng, <strong>Michael</strong> I. Jordan, and Stuart Russell. Distance metric learning, with application to clustering with side-information. In Advances in Neural Information Processing Systems 15, pages 505?512, 2002. 8 [6] Alexandre d?Aspremont, Laurent El Ghaoui, Mic...</p>
  492. <div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  493. </div>
  494.  
  495. <div class="result-row">
  496. <h5 style="width: 80%;"><strong id="result_index">44</strong> Multiplicative Updating Rule for Blind Separation Derived from the Method of Scoring</h5>
  497. <p style="float: right; margin-top: -40px; color: lightgray;">0.08027043</p>
  498. <h6><strong id="year">1997</strong> - <a href="/search?q=authors:%22Howard Hua Yang%22">Howard Hua Yang</a></h6>
  499. <p class="light">...MIT Press: Cambridge, MA., pages 127-133, 1997. [3] S. Amari, A. Cichocki, and H. H. Yang. A new learning algorithm for blind [4] [5] [6] [7] [8] signal separation. In Advances in Neural Information Processing Systems, 8, eds. David S. Touretzky, <strong>Michael</strong> C. Mozer and <strong>Michael</strong> E. Hasselmo, MIT Press: Cambridge, MA., pages 757-763, 1996. J.-F. Cardoso. Infomax and maximum likelihood for blind source separation. IEEE Signal Processing Letters, April 1997. J.-F. Cardoso and B. Laheld. Equivariant ...</p>
  500. <div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div>
  501. </div>
  502.  
  503. <div class="result-row">
  504. <h5 style="width: 80%;"><strong id="result_index">45</strong> On the Non-Existence of a Universal Learning Algorithm for Recurrent Neural Networks</h5>
  505. <p style="float: right; margin-top: -40px; color: lightgray;">0.07985056</p>
  506. <h6><strong id="year">1993</strong> - <a href="/search?q=authors:%22Herbert Wiklicky%22">Herbert Wiklicky</a></h6>
  507. <p class="light">...s zur Forderung der wissenschaftlichen Forschung&#x27; as Projekt J0828-PHY. References [Blum and Rivest, 1992] Avrim L. Blum and Ronald L. Rivest. Training a 3-node neural network is NP-complete. Neural Networks, 5:117-127,1992. [Cosnard et al. , 1993] <strong>Michael</strong> Cosnard, Max Garzon, and Pascal Koiran. Computability properties of low-dimensional dynamical systems. In Symposium on Theoretical Aspects of Computer Science (STACS &#x27;93), pages 365-373, Springer-Verlag, BerlinNew York, 1993. [Davis, 1973] Ma...</p>
  508. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%225%22">Topic 5 &lt;network layer model deep...&gt;</a></div>
  509. </div>
  510.  
  511. <div class="result-row">
  512. <h5 style="width: 80%;"><strong id="result_index">46</strong> Global Regularization of Inverse Kinematics for Redundant Manipulators</h5>
  513. <p style="float: right; margin-top: -40px; color: lightgray;">0.07974386</p>
  514. <h6><strong id="year">1992</strong> - <a href="/search?q=authors:%22David DeMers%22">David DeMers</a>, <a href="/search?q=authors:%22Kenneth Kreutz-Delgado%22">Kenneth Kreutz-Delgado</a></h6>
  515. <p class="light">...n Craig (1986).Introduction to Robotics. David DeMers &amp; Kenneth Kreutz-Delgado (1992). &#x27;&#x27;Learning Global Direct Inverse Kinematics&#x27;&#x27; in Moody, J. E .? Hanson. SJ. and Lippmann, R.P.? eds, Advances in Neural Information Processing Systems 4. 589-594. <strong>Michael</strong> 1. Jordan &amp; David Rumelhart (1992), &#x27;Forward Models: Supervised Learning with a Distal Teacher&#x27;, Cognitive Science 16,307-354. J. Kindermann &amp; Alexander Linden (1990), &#x27;Inversion of Neural Networks by Gradient Descent&#x27;. 1. Parallel Computing ...</p>
  516. <div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  517. </div>
  518.  
  519. <div class="result-row">
  520. <h5 style="width: 80%;"><strong id="result_index">47</strong> High Performance Neural Net Simulation on a Multiprocessor System with &#34;Intelligent&#34; Communication</h5>
  521. <p style="float: right; margin-top: -40px; color: lightgray;">0.0795965</p>
  522. <h6><strong id="year">1993</strong> - <a href="/search?q=authors:%22Urs A. M?ller%22">Urs A. M?ller</a>, <a href="/search?q=authors:%22Michael Kocheisen%22">Michael Kocheisen</a>, <a href="/search?q=authors:%22Anton Gunzinger%22">Anton Gunzinger</a></h6>
  523. <p class="light">High Performance Neural Net Simulation on a Multiprocessor System with &#x27;Intelligent&#x27; Communication Urs A. Miiller, <strong>Michael</strong> Kocheisen, and Anton Gunzinger Electronics Laboratory, Swiss Federal Institute of Technology CH-B092 Zurich, Switzerland Abstract The performance requirements in experimental research on artificial neural nets often exceed the capability of ...</p>
  524. <div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2222%22">Topic 22 &lt;signal source circuit time...&gt;</a></div>
  525. </div>
  526.  
  527. <div class="result-row">
  528. <h5 style="width: 80%;"><strong id="result_index">48</strong> Data Visualization and Feature Selection: New Algorithms for Nongaussian Data</h5>
  529. <p style="float: right; margin-top: -40px; color: lightgray;">0.07900001</p>
  530. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22John Moody%22">John Moody</a>, <a href="/search?q=authors:%22Howard Hua Yang%22">Howard Hua Yang</a></h6>
  531. <p class="light">... This research was supported by grant ONR N00014-96-10476. References [1] S. Amari, A. Cichocki, and H. H. Yang. A new learning algorithm for blind signal separation. In Advances in Neural Information Processing Systems, 8, eds. David S. Touretzky, <strong>Michael</strong> C. Mozer and <strong>Michael</strong> E. Hasselmo, MIT Press: Cambridge, MA., pages 757-763, 1996. [2] G. Barrows and J. Sciortino. A mutual information measure for feature selection with application to pulse classification. In IEEE Intern. Symposium on TimeF...</p>
  532. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  533. </div>
  534.  
  535. <div class="result-row">
  536. <h5 style="width: 80%;"><strong id="result_index">49</strong> Learning Hybrid Models for Image Annotation with Partially Labeled Data</h5>
  537. <p style="float: right; margin-top: -40px; color: lightgray;">0.078963466</p>
  538. <h6><strong id="year">2008</strong> - <a href="/search?q=authors:%22Richard S. Zemel%22">Richard S. Zemel</a>, <a href="/search?q=authors:%22Xuming He%22">Xuming He</a></h6>
  539. <p class="light">...asemin Altun, David McAllester, and Mikhail Belkin. Maximum margin semi-supervised learning for structured variables. In NIPS 18, 2006. [2] David Blei and Jon McAuliffe. Supervised topic models. In NIPS 20, 2008. [3] David M. Blei, Andrew Y. Ng, and <strong>Michael</strong> I. Jordan. Latent Dirichlet allocation. J. Mach. Learn. Res., 3:993?1022, 2003. [4] Xuming He, Richard Zemel, and Miguel Carreira-Perpinan. Multiscale conditional random fields for image labelling. In CVPR, 2004. [5] Xuming He, Richard S. Zem...</p>
  540. <div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  541. </div>
  542.  
  543. <div class="result-row">
  544. <h5 style="width: 80%;"><strong id="result_index">50</strong> Convergence of Stochastic Iterative Dynamic Programming Algorithms</h5>
  545. <p style="float: right; margin-top: -40px; color: lightgray;">0.077568054</p>
  546. <h6><strong id="year">1993</strong> - <a href="/search?q=authors:%22Michael I. Jordan%22">Michael I. Jordan</a>, <a href="/search?q=authors:%22Satinder P. Singh%22">Satinder P. Singh</a>, <a href="/search?q=authors:%22Tommi Jaakkola%22">Tommi Jaakkola</a></h6>
  547. <p class="light">Convergence of Stochastic Iterative Dynamic Programming Algorithms Tommi Jaakkola&#x27;&#x27; <strong>Michael</strong> I. Jordan Satinder P. Singh Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge, MA 02139 Abstract Increasing attention has recently been paid to algorithms based on dynamic programming (DP) due to the ...</p>
  548. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  549. </div>
  550.  
  551. <div class="result-row">
  552. <h5 style="width: 80%;"><strong id="result_index">51</strong> Covariance shrinkage for autocorrelated data</h5>
  553. <p style="float: right; margin-top: -40px; color: lightgray;">0.07729362</p>
  554. <h6><strong id="year">2014</strong> - <a href="/search?q=authors:%22Klaus-Robert M?ller%22">Klaus-Robert M?ller</a>, <a href="/search?q=authors:%22Daniel Bartz%22">Daniel Bartz</a></h6>
  555. <p class="light">...rning. Springer, 2008. [LG11] Fabien Lotte and Cuntai Guan. Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. Biomedical Engineering, IEEE Transactions on, 58(2):355? 362, 2011. [LW04] Olivier Ledoit and <strong>Michael</strong> Wolf. A well-conditioned estimator for large-dimensional covariance matrices. Journal of Multivariate Analysis, 88(2):365?411, 2004. [LW12] Olivier Ledoit and <strong>Michael</strong> Wolf. Nonlinear shrinkage estimation of large-dimensional covariance matric...</p>
  556. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  557. </div>
  558.  
  559. <div class="result-row">
  560. <h5 style="width: 80%;"><strong id="result_index">52</strong> Approximate inference in continuous time Gaussian-Jump processes</h5>
  561. <p style="float: right; margin-top: -40px; color: lightgray;">0.077280246</p>
  562. <h6><strong id="year">2010</strong> - <a href="/search?q=authors:%22Manfred Opper%22">Manfred Opper</a>, <a href="/search?q=authors:%22Andreas Ruttor%22">Andreas Ruttor</a>, <a href="/search?q=authors:%22Guido Sanguinetti%22">Guido Sanguinetti</a></h6>
  563. <p class="light">... Markov processes. In David Barber, Taylan Cemgil, and Silvia Chiappa, editors, Inference and Learning in Dynamic Models. Cambridge University Press, 2010. [12] M. A. Lifshits. Gaussian Random Functions. Kluwer, Dordrecht, second edition, 1995. [13] <strong>Michael</strong> I. Jordan, Zoubin Ghahramani, Tommi S. Jaakkola, and Lawrence K. Saul. An introduction to variational methods for graphical models. Machine Learning, 37:183?233, 1999. [14] Manfred Opper and Guido Sanguinetti. Learning combinatorial transcrip...</p>
  564. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  565. </div>
  566.  
  567. <div class="result-row">
  568. <h5 style="width: 80%;"><strong id="result_index">53</strong> Correlated Neuronal Response: Time Scales and Mechanisms</h5>
  569. <p style="float: right; margin-top: -40px; color: lightgray;">0.0760926</p>
  570. <h6><strong id="year">1995</strong> - <a href="/search?q=authors:%22Christof Koch%22">Christof Koch</a>, <a href="/search?q=authors:%22Wyeth Bair%22">Wyeth Bair</a>, <a href="/search?q=authors:%22Ehud Zohary%22">Ehud Zohary</a></h6>
  571. <p class="light">...tion between spike count. Correlation in spike count is an important factor that can limit the useful pool-size of neuronal ensembles (Zohary et al., 1994; Gawne and Richmond, 1993). Acknowledgements We thank William T. Newsome, Kenneth H. Britten, <strong>Michael</strong> N. Shadlen, and J. Anthony Movshon for kindly providing data that was recorded in previous studies and for helpful discussion. This work was funded by the Office of Naval Research and the Air Force Office of Scientific Research. W. B. was sup...</p>
  572. <div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2218%22">Topic 18 &lt;neuron spike time input...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  573. </div>
  574.  
  575. <div class="result-row">
  576. <h5 style="width: 80%;"><strong id="result_index">54</strong> Regret Minimization in Games with Incomplete Information</h5>
  577. <p style="float: right; margin-top: -40px; color: lightgray;">0.07527273</p>
  578. <h6><strong id="year">2007</strong> - <a href="/search?q=authors:%22Michael Bowling%22">Michael Bowling</a>, <a href="/search?q=authors:%22Martin Zinkevich%22">Martin Zinkevich</a>, <a href="/search?q=authors:%22Michael Johanson%22">Michael Johanson</a>, <a href="/search?q=authors:%22Carmelo Piccione%22">Carmelo Piccione</a></h6>
  579. <p class="light">Regret Minimization in Games with Incomplete Information Martin Zinkevich maz@cs.ualberta.ca <strong>Michael</strong> Johanson johanson@cs.ualberta.ca Carmelo Piccione Computing Science Department University of Alberta Edmonton, AB Canada T6G2E8 carm@cs.ualberta.ca <strong>Michael</strong> Bowling Computing Science Department University of Alberta Edmonton, AB Canada T6G2E8...</p>
  580. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div>
  581. </div>
  582.  
  583. <div class="result-row">
  584. <h5 style="width: 80%;"><strong id="result_index">55</strong> Incremental Gaussian Processes</h5>
  585. <p style="float: right; margin-top: -40px; color: lightgray;">0.07502656</p>
  586. <h6><strong id="year">2002</strong> - <a href="/search?q=authors:%22Ole Winther%22">Ole Winther</a>, <a href="/search?q=authors:%22Joaquin Qui?onero Candela%22">Joaquin Qui?onero Candela</a></h6>
  587. <p class="light">...thods should also be applicable beyond supervised learning. Acknowledgments JQC is funded by the EU Multi-Agent Control Research Training Network - EC TMR grant HPRNCT-1999-00107. We thank Lars Kai Hansen for very useful discussions. References [1] <strong>Michael</strong> E. Tipping, ?Sparse bayesian learning and the relevance vector machine,? Journal of Machine Learning Research, vol. 1, pp. 211?244, 2001. [2] Vladimir N. Vapnik, Statistical Learning Theory, Wiley, New York, 1998. [3] Bernhard Sch?olkopf and ...</p>
  588. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div>
  589. </div>
  590.  
  591. <div class="result-row">
  592. <h5 style="width: 80%;"><strong id="result_index">56</strong> Quantized Estimation of Gaussian Sequence Models in Euclidean Balls</h5>
  593. <p style="float: right; margin-top: -40px; color: lightgray;">0.07446515</p>
  594. <h6><strong id="year">2014</strong> - <a href="/search?q=authors:%22Yuancheng Zhu%22">Yuancheng Zhu</a>, <a href="/search?q=authors:%22John Lafferty%22">John Lafferty</a></h6>
  595. <p class="light">...earning Research, 14(1):1837?1864, 2013. [2] T. Tony Cai and Tiefeng Jiang. Phase transition in limiting distributions of coherence of highdimensional random matrices. Journal of Multivariate Analysis, 107:24?39, 2012. [3] Venkat Chandrasekarana and <strong>Michael</strong> I. Jordan. Computational and statistical tradeoffs via convex relaxation. PNAS, 110(13):E1181?E1190, March 2013. [4] David L. Donoho. Wald lecture I: Counting bits with Kolmogorov and Shannon. 2000. [5] Stark C. Draper and Gregory W. Wornell....</p>
  596. <div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  597. </div>
  598.  
  599. <div class="result-row">
  600. <h5 style="width: 80%;"><strong id="result_index">57</strong> Adaptive Regularization for Transductive Support Vector Machine</h5>
  601. <p style="float: right; margin-top: -40px; color: lightgray;">0.07423846</p>
  602. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Rong Jin%22">Rong Jin</a>, <a href="/search?q=authors:%22Zenglin Xu%22">Zenglin Xu</a>, <a href="/search?q=authors:%22Jianke Zhu%22">Jianke Zhu</a>, <a href="/search?q=authors:%22Irwin King%22">Irwin King</a>, <a href="/search?q=authors:%22Michael Lyu%22">Michael Lyu</a>, <a href="/search?q=authors:%22Zhirong Yang%22">Zhirong Yang</a></h6>
  603. <p class="light">...ation for Transductive Support Vector Machine Zenglin Xu ?? Cluster MMCI Saarland Univ. &amp; MPI INF Saarbrucken, Germany zlxu@mpi-inf.mpg.de ? Rong Jin Computer Sci. &amp; Eng. Michigan State Univ. East Lansing, MI, U.S. rongjin@cse.msu.edu Irwin King? <strong>Michael</strong> R. Lyu? ? Computer Science &amp; Engineering The Chinese Univ. of Hong Kong Shatin, N.T., Hong Kong {king,lyu}@cse.cuhk.edu.hk Jianke Zhu Computer Vision Lab ETH Zurich Zurich, Switzerland zhuji@vision.ee.ethz.ch Zhirong Yang Information &amp; Comp...</p>
  604. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div>
  605. </div>
  606.  
  607. <div class="result-row">
  608. <h5 style="width: 80%;"><strong id="result_index">58</strong> Coding Time-Varying Signals Using Sparse, Shift-Invariant Representations</h5>
  609. <p style="float: right; margin-top: -40px; color: lightgray;">0.07397773</p>
  610. <h6><strong id="year">1998</strong> - <a href="/search?q=authors:%22Terrence J. Sejnowski%22">Terrence J. Sejnowski</a>, <a href="/search?q=authors:%22Michael S. Lewicki%22">Michael S. Lewicki</a></h6>
  611. <p class="light">Coding time-varying signals using sparse, shift-invariant representations Terrence J. Sejnowski terryCsalk.edu <strong>Michael</strong> S. Lewicki* lewickiCsalk.edu Howard Hughes Medical Institute Computational Neurobiology Laboratory The Salk Institute 10010 N. Torrey Pines Rd. La Jolla, CA 92037 Abstract A common way to represent a time series is to divide it into shortdu...</p>
  612. <div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2222%22">Topic 22 &lt;signal source circuit time...&gt;</a></div>
  613. </div>
  614.  
  615. <div class="result-row">
  616. <h5 style="width: 80%;"><strong id="result_index">59</strong> Robust Portfolio Optimization</h5>
  617. <p style="float: right; margin-top: -40px; color: lightgray;">0.07394368</p>
  618. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Han Liu%22">Han Liu</a>, <a href="/search?q=authors:%22Fang Han%22">Fang Han</a>, <a href="/search?q=authors:%22Huitong Qiu%22">Huitong Qiu</a>, <a href="/search?q=authors:%22Brian Caffo%22">Brian Caffo</a></h6>
  619. <p class="light">...upper bound on the percentage of short positions. In practice, the percentage of short positions is usually strictly controlled to be much lower. 8 References [1] Harry Markowitz. Portfolio selection. The Journal of Finance, 7(1):77?91, 1952. [2] <strong>Michael</strong> J Best and Robert R Grauer. On the sensitivity of mean-variance-efficient portfolios to changes in asset means: some analytical and computational results. Review of Financial Studies, 4(2):315?342, 1991. [3] Vijay Kumar Chopra and William T Z...</p>
  620. <div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div>
  621. </div>
  622.  
  623. <div class="result-row">
  624. <h5 style="width: 80%;"><strong id="result_index">60</strong> Learning with a Wasserstein Loss</h5>
  625. <p style="float: right; margin-top: -40px; color: lightgray;">0.07359761</p>
  626. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Charlie Frogner%22">Charlie Frogner</a>, <a href="/search?q=authors:%22Mauricio Araya%22">Mauricio Araya</a>, <a href="/search?q=authors:%22Chiyuan Zhang%22">Chiyuan Zhang</a>, <a href="/search?q=authors:%22Hossein Mobahi%22">Hossein Mobahi</a>, <a href="/search?q=authors:%22Tomaso A. Poggio%22">Tomaso A. Poggio</a></h6>
  627. <p class="light">...g, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. CVPR (to appear), 2015. [2] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, <strong>Michael</strong> Bernstein, Alexander C. Berg, and Li Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 2015. [3] Marco Cuturi and Arnaud Doucet. Fast Computation of Wasserstein Barycenters. ICML, 201...</p>
  628. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  629. </div>
  630.  
  631. <div class="result-row">
  632. <h5 style="width: 80%;"><strong id="result_index">61</strong> Instance-Based State Identification for Reinforcement Learning</h5>
  633. <p style="float: right; margin-top: -40px; color: lightgray;">0.07329909</p>
  634. <h6><strong id="year">1994</strong> - <a href="/search?q=authors:%22R. Andrew McCallum%22">R. Andrew McCallum</a></h6>
  635. <p class="light">...Control. Academic Press, 1978. [Chrisman, 1992] Lonnie Chrisman. Reinforcement learning with perceptual aliasing: The perceptual distinctions approach. In Tenth Nat&#x27;l Conf. on AI, 1992. [Jaakkola et al., 1995] Tommi Jaakkola, Satinder Pal Singh, and <strong>Michael</strong> 1. Jordan. Reinforcement learning algorithm for partially observable markov decision problems. In Advances of Neural Information Processing Systems 7. Morgan Kaufmann, 1995. [Lin, 1993] Long-Ji Lin. Reinforcement Learning for Robots Using Neu...</p>
  636. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div>
  637. </div>
  638.  
  639. <div class="result-row">
  640. <h5 style="width: 80%;"><strong id="result_index">62</strong> Plasticity Kernels and Temporal Statistics</h5>
  641. <p style="float: right; margin-top: -40px; color: lightgray;">0.073277436</p>
  642. <h6><strong id="year">2003</strong> - <a href="/search?q=authors:%22Peter Dayan%22">Peter Dayan</a>, <a href="/search?q=authors:%22Michael H?usser%22">Michael H?usser</a>, <a href="/search?q=authors:%22Michael London%22">Michael London</a></h6>
  643. <p class="light">Plasticity Kernels and Temporal Statistics Peter Dayan1 <strong>Michael</strong> Hausser 2 <strong>Michael</strong> London1?2 1GCNU, 2WIBR, Dept of Physiology UCL, Gower Street, London dayan@gats5y.ucl.ac.uk {m.hausser,m.london}@ucl.ac.uk Abstract Computational mysteries surround the kernels relating the magnitude and sign of changes i...</p>
  644. <div class="chip"><a href="/search?q=topic:%2218%22">Topic 18 &lt;neuron spike time input...&gt;</a></div><div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2222%22">Topic 22 &lt;signal source circuit time...&gt;</a></div>
  645. </div>
  646.  
  647. <div class="result-row">
  648. <h5 style="width: 80%;"><strong id="result_index">63</strong> Sparsistent Learning of Varying-coefficient Models with Structural Changes</h5>
  649. <p style="float: right; margin-top: -40px; color: lightgray;">0.07265642</p>
  650. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Eric P. Xing%22">Eric P. Xing</a>, <a href="/search?q=authors:%22Le Song%22">Le Song</a>, <a href="/search?q=authors:%22Mladen Kolar%22">Mladen Kolar</a></h6>
  651. <p class="light">...sso and dantzig selector. Ann. of Stat. [7] Florentina Bunea. Honest variable selection in linear and logistic regression models via ?1 and ?1 + ?2 penalization. Electronic Journal of Statistics, 2:1153, 2008. [8] Scott S. Chen, David L. Donoho, and <strong>Michael</strong> A. Saunders. Atomic decomposition by basis pursuit. SIAM Journal on Scientific Computing, 20(1):33?61, 1999. [9] William S. Cleveland, Eric Grosse, and William M. Shyu. Local regression models. In John M. Chambers and Trevor J. Hastie, editor...</p>
  652. <div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  653. </div>
  654.  
  655. <div class="result-row">
  656. <h5 style="width: 80%;"><strong id="result_index">64</strong> Stable adaptive control with online learning</h5>
  657. <p style="float: right; margin-top: -40px; color: lightgray;">0.07250018</p>
  658. <h6><strong id="year">2004</strong> - <a href="/search?q=authors:%22Andrew Y. Ng%22">Andrew Y. Ng</a>, <a href="/search?q=authors:%22H. J. Kim%22">H. J. Kim</a></h6>
  659. <p class="light">...rl Astrom and Bjorn Wittenmark. Adaptive Control (2nd Edition). Addison-Wesley, 1994. [3] V. D. Blondel and J. N. Tsitsiklis. The boundedness of all products of a pair of matrices is undecidable. Systems and Control Letters, 41(2):135?140, 2000. [4] <strong>Michael</strong> S. Branicky. Analyzing continuous switching systems: Theory and examples. In Proc. American Control Conference, 1994. [5] <strong>Michael</strong> S. Branicky. Stability of switched and hybrid systems. In Proc. 33rd IEEE Conf. Decision Control, 1994. [6] G. F...</p>
  660. <div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div>
  661. </div>
  662.  
  663. <div class="result-row">
  664. <h5 style="width: 80%;"><strong id="result_index">65</strong> Cholinergic Modulation May Enhance Cortical Associative Memory Function</h5>
  665. <p style="float: right; margin-top: -40px; color: lightgray;">0.07245657</p>
  666. <h6><strong id="year">1990</strong> - <a href="/search?q=authors:%22James M. Bower%22">James M. Bower</a>, <a href="/search?q=authors:%22Michael E. Hasselmo%22">Michael E. Hasselmo</a>, <a href="/search?q=authors:%22Brooke P. Anderson%22">Brooke P. Anderson</a></h6>
  667. <p class="light">Cholinergic Modulation May Enhance Cortical Associative Memory Function <strong>Michael</strong> E. Hasselmo? Computation and Neural Systems Caltech 216-76 Pasadena, CA 91125 Brooke P. Andersont Computation and Neural Systems Caltech 139-74 Pasadena, CA 91125 James M. Bower Computation and Neural Systems Caltech 216-76 Pasadena, CA 911...</p>
  668. <div class="chip"><a href="/search?q=topic:%2218%22">Topic 18 &lt;neuron spike time input...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div>
  669. </div>
  670.  
  671. <div class="result-row">
  672. <h5 style="width: 80%;"><strong id="result_index">66</strong> Online Learning of Assignments</h5>
  673. <p style="float: right; margin-top: -40px; color: lightgray;">0.071930155</p>
  674. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Andreas Krause%22">Andreas Krause</a>, <a href="/search?q=authors:%22Matthew Streeter%22">Matthew Streeter</a>, <a href="/search?q=authors:%22Daniel Golovin%22">Daniel Golovin</a></h6>
  675. <p class="light">...roid constraint. SIAM Journal on Computing. To appear. [5] Nicol`o Cesa-Bianchi, Yoav Freund, David Haussler, David P. Helmbold, Robert E. Schapire, and Manfred K. Warmuth. How to use expert advice. J. ACM, 44(3):427?485, 1997. [6] Benjamin Edelman, <strong>Michael</strong> Ostrovsky, and <strong>Michael</strong> Schwarz. Internet advertising and the generalized second price auction: Selling billions of dollars worth of keywords. American Economic Review, 97(1):242? 259, 2007. [7] Jon Feldman and S. Muthukrishnan. Algorithmic me...</p>
  676. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div>
  677. </div>
  678.  
  679. <div class="result-row">
  680. <h5 style="width: 80%;"><strong id="result_index">67</strong> The Brain Uses Reliability of Stimulus Information when Making Perceptual Decisions</h5>
  681. <p style="float: right; margin-top: -40px; color: lightgray;">0.07179651</p>
  682. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Sebastian Bitzer%22">Sebastian Bitzer</a>, <a href="/search?q=authors:%22Stefan Kiebel%22">Stefan Kiebel</a></h6>
  683. <p class="light">...n a trial. First models of simultaneous decision making and reliability estimation have been suggested [21], but clearly more work in this direction is needed to elucidate the underlying mechanism used by the brain. References [1] Joshua I Gold and <strong>Michael</strong> N Shadlen. The neural basis of decision making. Annu Rev Neurosci, 30:535?574, 2007. [2] I. D. John. A statistical decision theory of simple reaction time. Australian Journal of Psychology, 19(1):27?34, 1967. 8 [3] R. Duncan Luce. Response ...</p>
  684. <div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div>
  685. </div>
  686.  
  687. <div class="result-row">
  688. <h5 style="width: 80%;"><strong id="result_index">68</strong> Assessing Approximations for Gaussian Process Classification</h5>
  689. <p style="float: right; margin-top: -40px; color: lightgray;">0.07141906</p>
  690. <h6><strong id="year">2005</strong> - <a href="/search?q=authors:%22Carl E. Rasmussen%22">Carl E. Rasmussen</a>, <a href="/search?q=authors:%22Malte Kuss%22">Malte Kuss</a></h6>
  691. <p class="light">...me of the European Community, under the PASCAL Network of Excellence, IST2002-506778. This publication only reflects the authors? views. References [1] C. K. I. Williams and C. E. Rasmussen. Gaussian processes for regression. In David S. Touretzky, <strong>Michael</strong> C. Mozer, and <strong>Michael</strong> E. Hasselmo, editors, NIPS 8, pages 514?520. MIT Press, 1996. [2] M. Kuss and C. E. Rasmussen. Assessing approximate inference for binary Gaussian process classification. Journal of Machine Learning Research, 6:1679?1704...</p>
  692. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  693. </div>
  694.  
  695. <div class="result-row">
  696. <h5 style="width: 80%;"><strong id="result_index">69</strong> Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes</h5>
  697. <p style="float: right; margin-top: -40px; color: lightgray;">0.07120952</p>
  698. <h6><strong id="year">2003</strong> - <a href="/search?q=authors:%22William T. Freeman%22">William T. Freeman</a>, <a href="/search?q=authors:%22Kevin P. Murphy%22">Kevin P. Murphy</a>, <a href="/search?q=authors:%22Antonio Torralba%22">Antonio Torralba</a></h6>
  699. <p class="light">...eport, Dept. Comp. Sci. U. Rochester, 2003. [4] D. Davon. Forest before the trees: the precedence of global features in visual perception. Cognitive Psychology, 9:353?383, 1977. [5] Pinary Duygulu, Kobus Barnard, Nando de Freitas, David Forsyth, and <strong>Michael</strong> I. Jordan. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In Proc. European Conf. on Computer Vision, 2002. [6] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervised scal...</p>
  700. <div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div>
  701. </div>
  702.  
  703. <div class="result-row">
  704. <h5 style="width: 80%;"><strong id="result_index">70</strong> Regularized Distance Metric Learning:Theory and Algorithm</h5>
  705. <p style="float: right; margin-top: -40px; color: lightgray;">0.07110751</p>
  706. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Rong Jin%22">Rong Jin</a>, <a href="/search?q=authors:%22Shijun Wang%22">Shijun Wang</a>, <a href="/search?q=authors:%22Yang Zhou%22">Yang Zhou</a></h6>
  707. <p class="light">...05. [6] Steven C.H. Hoi, Wei Liu, and Shih-Fu Chang. Semi-supervised distance metric learning for collaborative image retrieval. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008. [7] Steven C.H. Hoi, Wei Liu, <strong>Michael</strong> R. Lyu, and Wei-Ying Ma. Learning distance metrics with contextual constraints for image retrieval. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2006. [8] L. K. Saul and S. T. Roweis. Think globally, fi...</p>
  708. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  709. </div>
  710.  
  711. <div class="result-row">
  712. <h5 style="width: 80%;"><strong id="result_index">71</strong> The Pareto Regret Frontier</h5>
  713. <p style="float: right; margin-top: -40px; color: lightgray;">0.07042667</p>
  714. <h6><strong id="year">2013</strong> - <a href="/search?q=authors:%22Wouter M. Koolen%22">Wouter M. Koolen</a></h6>
  715. <p class="light">...rthik Sridharan. Relax and randomize : From value to algorithms. In P. Bartlett, F.C.N. Pereira, C.J.C. Burges, L. Bottou, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems 25, pages 2150?2158, 2012. [10] Eyal Even-Dar, <strong>Michael</strong> Kearns, Yishay Mansour, and Jennifer Wortman. Regret to the best vs. regret to the average. Machine Learning, 72(1-2):21?37, 2008. [11] <strong>Michael</strong> Kapralov and Rina Panigrahy. Prediction strategies without loss. In J. Shawe-Taylor, R.S. Zemel, P...</p>
  716. <div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div>
  717. </div>
  718.  
  719. <div class="result-row">
  720. <h5 style="width: 80%;"><strong id="result_index">72</strong> The Human Kernel</h5>
  721. <p style="float: right; margin-top: -40px; color: lightgray;">0.0696219</p>
  722. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Chris Lucas%22">Chris Lucas</a>, <a href="/search?q=authors:%22Eric P. Xing%22">Eric P. Xing</a>, <a href="/search?q=authors:%22Andrew G. Wilson%22">Andrew G. Wilson</a>, <a href="/search?q=authors:%22Christoph Dann%22">Christoph Dann</a></h6>
  723. <p class="light">...R.P.N. Rao. Bayesian brain: probabilistic approaches to neural coding. MIT Press, 2007. [4] Zoubin Ghahramani. Probabilistic machine learning and artificial intelligence. Nature, 521(7553):452? 459, 2015. [5] Daniel M Wolpert, Zoubin Ghahramani, and <strong>Michael</strong> I Jordan. An internal model for sensorimotor integration. Science, 269(5232):1880?1882, 1995. [6] David C Knill and Whitman Richards. Perception as Bayesian inference. Cambridge University Press, 1996. [7] Sophie Deneve. Bayesian spiking neur...</p>
  724. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div>
  725. </div>
  726.  
  727. <div class="result-row">
  728. <h5 style="width: 80%;"><strong id="result_index">73</strong> Blending Autonomous Exploration and Apprenticeship Learning</h5>
  729. <p style="float: right; margin-top: -40px; color: lightgray;">0.06927982</p>
  730. <h6><strong id="year">2011</strong> - <a href="/search?q=authors:%22Thomas J. Walsh%22">Thomas J. Walsh</a>, <a href="/search?q=authors:%22Daniel K. Hewlett%22">Daniel K. Hewlett</a>, <a href="/search?q=authors:%22Clayton T. Morrison%22">Clayton T. Morrison</a></h6>
  731. <p class="light">... guarantees the teacher will only provide demonstrations that attempt to teach concepts the agent could not tractably learn on its own, which has clear benefits when demonstrations are far more costly than exploration steps. Acknowledgments We thank <strong>Michael</strong> Littman and Lihong Li for discussions and DARPA-27001328 for funding. 8 References [1] Pieter Abbeel and Andrew Y. Ng. Exploration and apprenticeship learning in reinforcement learning. In ICML, 2005. [2] Richard S. Sutton and Andrew G. Ba...</p>
  732. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  733. </div>
  734.  
  735. <div class="result-row">
  736. <h5 style="width: 80%;"><strong id="result_index">74</strong> Learning concept graphs from text with stick-breaking priors</h5>
  737. <p style="float: right; margin-top: -40px; color: lightgray;">0.068723574</p>
  738. <h6><strong id="year">2010</strong> - <a href="/search?q=authors:%22Padhraic Smyth%22">Padhraic Smyth</a>, <a href="/search?q=authors:%22Mark Steyvers%22">Mark Steyvers</a>, <a href="/search?q=authors:%22America Chambers%22">America Chambers</a></h6>
  739. <p class="light">...holarship (AC), and by a Google Faculty Research award (PS). The authors would also like to thank Ian Porteous and Alex Ihler for useful discussions. 4 MALLET implements the ?exit node? version of hPAM 8 References [1] David Blei, Andrew Ng, and <strong>Michael</strong> Jordan. Latent dirichlet allocation. Journal of Machine Learning Research, 3:993?1022, 2003. [2] David M. Blei, Thomas L. Griffiths, and <strong>Michael</strong> I. Jordan. The nested chinese restaurant process and bayesian nonparametric inference of topic hi...</p>
  740. <div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div>
  741. </div>
  742.  
  743. <div class="result-row">
  744. <h5 style="width: 80%;"><strong id="result_index">75</strong> Potential Boosters?</h5>
  745. <p style="float: right; margin-top: -40px; color: lightgray;">0.06712993</p>
  746. <h6><strong id="year">1999</strong> - <a href="/search?q=authors:%22David P. Helmbold%22">David P. Helmbold</a>, <a href="/search?q=authors:%22Nigel Duffy%22">Nigel Duffy</a></h6>
  747. <p class="light">...gorithm [12] that uses a time-varying sigmoidal potential. It would be interesting to adapt our techniques to such dynamic potentials. References [1] Robert E. Schapire. The Design and Analysis of Efficient Learning Algorithms. MIT Press, 1992. [2] <strong>Michael</strong> Kearns and Leslie Valiant . Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the ACM, 41(1):67-95, January 1994. [3] L. G. Valiant. A theory of the learnable. Commun. ACM, 27(11):1134-1142, November 1984....</p>
  748. <div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  749. </div>
  750.  
  751. <div class="result-row">
  752. <h5 style="width: 80%;"><strong id="result_index">76</strong> Bayesian Kernel Shaping for Learning Control</h5>
  753. <p style="float: right; margin-top: -40px; color: lightgray;">0.06695148</p>
  754. <h6><strong id="year">2008</strong> - <a href="/search?q=authors:%22Stefan Schaal%22">Stefan Schaal</a>, <a href="/search?q=authors:%22Sethu Vijayakumar%22">Sethu Vijayakumar</a>, <a href="/search?q=authors:%22Jo-anne Ting%22">Jo-anne Ting</a>, <a href="/search?q=authors:%22Mrinal Kalakrishnan%22">Mrinal Kalakrishnan</a></h6>
  755. <p class="light">...utomatic relevant determination feature. Other future extensions include an online implementation of the local kernel shaping algorithm. References [1] C. K. I. Williams and C. E. Rasmussen. Gaussian processes for regression. In David S. Touretzky, <strong>Michael</strong> C. Mozer, and <strong>Michael</strong> E. Hasselmo, editors, In Advances in Neural Information Processing Systems 8, volume 8. MIT Press, 1995. [2] J. H. Friedman. A variable span smoother. Technical report, Stanford University, 1984. [3] T. Poggio and F. Gir...</p>
  756. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  757. </div>
  758.  
  759. <div class="result-row">
  760. <h5 style="width: 80%;"><strong id="result_index">77</strong> FPNN: Field Probing Neural Networks for 3D Data</h5>
  761. <p style="float: right; margin-top: -40px; color: lightgray;">0.06693096</p>
  762. <h6><strong id="year">2016</strong> - <a href="/search?q=authors:%22Leonidas J. Guibas%22">Leonidas J. Guibas</a>, <a href="/search?q=authors:%22Hao Su%22">Hao Su</a>, <a href="/search?q=authors:%22Yangyan Li%22">Yangyan Li</a>, <a href="/search?q=authors:%22Soeren Pirk%22">Soeren Pirk</a>, <a href="/search?q=authors:%22Charles R. Qi%22">Charles R. Qi</a></h6>
  763. <p class="light">...U. Castellani, and P. Vandergheynst. Learning classspecific descriptors for deformable shapes using localized spectral convolutional networks. In SGP, pages 13?23. Eurographics Association, 2015. [2] Davide Boscaini, Jonathan Masci, Emanuele Rodol?, <strong>Michael</strong> M Bronstein, and Daniel Cremers. Anisotropic diffusion descriptors. CGF, 35(2):431?441, 2016. [3] Alexander M. Bronstein, <strong>Michael</strong> M. Bronstein, Leonidas J. Guibas, and Maks Ovsjanikov. Shape google: Geometric words and expressions for invaria...</p>
  764. <div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div><div class="chip"><a href="/search?q=topic:%225%22">Topic 5 &lt;network layer model deep...&gt;</a></div><div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div>
  765. </div>
  766.  
  767. <div class="result-row">
  768. <h5 style="width: 80%;"><strong id="result_index">78</strong> Smoothed Gradients for Stochastic Variational Inference</h5>
  769. <p style="float: right; margin-top: -40px; color: lightgray;">0.06654047</p>
  770. <h6><strong id="year">2014</strong> - <a href="/search?q=authors:%22David Blei%22">David Blei</a>, <a href="/search?q=authors:%22Stephan Mandt%22">Stephan Mandt</a></h6>
  771. <p class="light">...nal on Optimization, 8(2):506?531, 1998. [14] Matthew Hoffman, Francis R Bach, and David M Blei. Online learning for latent Dirichlet allocation. In Advances in Neural Information Processing Systems, pages 856?864, 2010. [15] Martin J Wainwright and <strong>Michael</strong> I Jordan. Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning, 1(1-2):1?305, 2008. [16] Christopher M Bishop et al. Pattern Recognition and Machine Learning, volume 1. Springer New Yor...</p>
  772. <div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  773. </div>
  774.  
  775. <div class="result-row">
  776. <h5 style="width: 80%;"><strong id="result_index">79</strong> An EM Algorithm for Localizing Multiple Sound Sources in Reverberant Environments</h5>
  777. <p style="float: right; margin-top: -40px; color: lightgray;">0.06654047</p>
  778. <h6><strong id="year">2006</strong> - <a href="/search?q=authors:%22Tony Jebara%22">Tony Jebara</a>, <a href="/search?q=authors:%22Michael I. Mandel%22">Michael I. Mandel</a>, <a href="/search?q=authors:%22Daniel P. Ellis%22">Daniel P. Ellis</a></h6>
  779. <p class="light">An EM Algorithm for Localizing Multiple Sound Sources in Reverberant Environments <strong>Michael</strong> I. Mandel, Daniel P. W. Ellis LabROSA, Dept. of Electrical Engineering Columbia University New York, NY {mim,dpwe}@ee.columbia.edu Tony Jebara Dept. of Computer Science Columbia University New York, NY jebara@cs.columbia.edu Abstract We pre...</p>
  780. <div class="chip"><a href="/search?q=topic:%221%22">Topic 1 &lt;sequence speech model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2222%22">Topic 22 &lt;signal source circuit time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div>
  781. </div>
  782.  
  783. <div class="result-row">
  784. <h5 style="width: 80%;"><strong id="result_index">80</strong> Distributed Probabilistic Learning for Camera Networks with Missing Data</h5>
  785. <p style="float: right; margin-top: -40px; color: lightgray;">0.065340996</p>
  786. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Vladimir Pavlovic%22">Vladimir Pavlovic</a>, <a href="/search?q=authors:%22Sejong Yoon%22">Sejong Yoon</a></h6>
  787. <p class="light">...2, 2010. [13] Andrew R. Conn, Nicholas I. M. Gould, and Philippe L. Toint. A globally convergent augmented Lagrangian algorithm for optimization with general constraints and simple bounds. SIAM J. Numer. Anal., 28:545?572, February 1991. [14] Robert <strong>Michael</strong> Lewis and Virginia Torczon. A Globally Convergent Augmented Lagrangian Pattern Search Algorithm for Optimization with General Constraints and Simple Bounds. SIAM J. on Optimization, 12:1075?1089, April 2002. [15] Stephen Boyd, Neal Parikh, Er...</p>
  788. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div>
  789. </div>
  790.  
  791. <div class="result-row">
  792. <h5 style="width: 80%;"><strong id="result_index">81</strong> Multiple Instance Learning for Computer Aided Diagnosis</h5>
  793. <p style="float: right; margin-top: -40px; color: lightgray;">0.065340996</p>
  794. <h6><strong id="year">2006</strong> - <a href="/search?q=authors:%22Glenn M. Fung%22">Glenn M. Fung</a>, <a href="/search?q=authors:%22Balaji Krishnapuram%22">Balaji Krishnapuram</a>, <a href="/search?q=authors:%22Murat Dundar%22">Murat Dundar</a>, <a href="/search?q=authors:%22R. B. Rao%22">R. B. Rao</a></h6>
  795. <p class="light">...ascade, E. A. Kazerooni, and J. Wei. Computerized detection of pulmonary embolism in 3D computed tomographic (CT) images: vessel tracking and segmentation techniques. In Medical Imaging 2003: Image Processing. Edited by Sonka, Milan; Fitzpatrick, J. <strong>Michael</strong>. Proceedings of the SPIE, Volume 5032, pp. 1613-1620 (2003)., pages 1613?1620, May 2003. [13] D. Jemal, R. Tiwari, T. Murray, A. Ghafoor, A. Saumuels, E. Ward, E. Feuer, and M. Thun. Cancer statistics, 2004. [14] L. Bogoni, P. Cathier, M. Dun...</p>
  796. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div><div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div>
  797. </div>
  798.  
  799. <div class="result-row">
  800. <h5 style="width: 80%;"><strong id="result_index">82</strong> A Gaussian Process Model of Quasar Spectral Energy Distributions</h5>
  801. <p style="float: right; margin-top: -40px; color: lightgray;">0.06499172</p>
  802. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22Dustin Lang%22">Dustin Lang</a>, <a href="/search?q=authors:%22Ryan P. Adams%22">Ryan P. Adams</a>, <a href="/search?q=authors:%22Andrew Miller%22">Andrew Miller</a>, <a href="/search?q=authors:%22Albert Wu%22">Albert Wu</a>, <a href="/search?q=authors:%22Jeff Regier%22">Jeff Regier</a>, <a href="/search?q=authors:%22Jon McAuliffe%22">Jon McAuliffe</a>, <a href="/search?q=authors:%22Mr. Prabhat%22">Mr. Prabhat</a>, <a href="/search?q=authors:%22David Schlegel%22">David Schlegel</a></h6>
  803. <p class="light">...Nocedal. Updating quasi-newton matrices with limited storage. Mathematics of computation, 35(151):773?782, 1980. [13] Isabelle P?ris, Patrick Petitjean, ?ric Aubourg, Nicholas P Ross, Adam D Myers, Alina Streblyanska, Stephen Bailey, Patrick B Hall, <strong>Michael</strong> A Strauss, Scott F Anderson, et al. The Sloan digital sky survey quasar catalog: tenth data release. Astronomy &amp; Astrophysics, 563:A54, 2014. [14] Jeffrey Regier, Andrew Miller, Jon McAuliffe, Ryan Adams, Matt Hoffman, Dustin Lang, David Schl...</p>
  804. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div>
  805. </div>
  806.  
  807. <div class="result-row">
  808. <h5 style="width: 80%;"><strong id="result_index">83</strong> Generalization Errors and Learning Curves for Regression with Multi-task Gaussian Processes</h5>
  809. <p style="float: right; margin-top: -40px; color: lightgray;">0.064228155</p>
  810. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Kian M. Chai%22">Kian M. Chai</a></h6>
  811. <p class="light">...part by the EU through the PASCAL2 Network of Excellence. 8 References [1] Carl E. Rasmussen and Christopher K. I. Williams. Gaussian Processes for Machine Learning. MIT Press, Cambridge, Massachusetts, 2006. [2] Yee Whye Teh, Matthias Seeger, and <strong>Michael</strong> I. Jordan. Semiparametric latent factor models. In Robert G. Cowell and Zoubin Ghahramani, editors, Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics, pages 333?340. Society for Artificial Intelligence a...</p>
  812. <div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div>
  813. </div>
  814.  
  815. <div class="result-row">
  816. <h5 style="width: 80%;"><strong id="result_index">84</strong> A Quantitative Model of Counterfactual Reasoning</h5>
  817. <p style="float: right; margin-top: -40px; color: lightgray;">0.064217955</p>
  818. <h6><strong id="year">2001</strong> - <a href="/search?q=authors:%22Daniel Yarlett%22">Daniel Yarlett</a>, <a href="/search?q=authors:%22Michael Ramscar%22">Michael Ramscar</a></h6>
  819. <p class="light">A Quantitative Model of Counterfactual Reasoning <strong>Michael</strong> Ramscar Division of Informatics University of Edinburgh Edinburgh, Scotland michael@dai.ed.ac.uk Daniel Yarlett Division of Informatics University of Edinburgh Edinburgh, Scotland dany@cogsci.ed.ac.uk Abstract In this paper we explore two q...</p>
  820. <div class="chip"><a href="/search?q=topic:%229%22">Topic 9 &lt;model human subject task...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2215%22">Topic 15 &lt;model time datum process...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  821. </div>
  822.  
  823. <div class="result-row">
  824. <h5 style="width: 80%;"><strong id="result_index">85</strong> Attractive People: Assembling Loose-Limbed Models using Non-parametric Belief Propagation</h5>
  825. <p style="float: right; margin-top: -40px; color: lightgray;">0.064216346</p>
  826. <h6><strong id="year">2003</strong> - <a href="/search?q=authors:%22Michael Isard%22">Michael Isard</a>, <a href="/search?q=authors:%22Michael J. Black%22">Michael J. Black</a>, <a href="/search?q=authors:%22Leonid Sigal%22">Leonid Sigal</a>, <a href="/search?q=authors:%22Benjamin H. Sigelman%22">Benjamin H. Sigelman</a></h6>
  827. <p class="light">Attractive People: Assembling Loose-Limbed Models using Non-parametric Belief Propagation Leonid Sigal Department of Computer Science Brown University Providence, RI 02912 ls@cs.brown.edu <strong>Michael</strong> Isard Microsoft Research Silicon Valley Mountain View, CA 94043 misard@microsoft.com Benjamin H. Sigelman Department of Computer Science Brown University Providence, RI 02912 bhsigelm@cs.brown.edu <strong>Michael</strong> J. Black Department of Computer Sci...</p>
  828. <div class="chip"><a href="/search?q=topic:%227%22">Topic 7 &lt;image object feature model...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div>
  829. </div>
  830.  
  831. <div class="result-row">
  832. <h5 style="width: 80%;"><strong id="result_index">86</strong> Multi-task Gaussian Process Prediction</h5>
  833. <p style="float: right; margin-top: -40px; color: lightgray;">0.064216346</p>
  834. <h6><strong id="year">2007</strong> - <a href="/search?q=authors:%22Christopher Williams%22">Christopher Williams</a>, <a href="/search?q=authors:%22Edwin V. Bonilla%22">Edwin V. Bonilla</a>, <a href="/search?q=authors:%22Kian M. Chai%22">Kian M. Chai</a></h6>
  835. <p class="light">...ceedings of the 11th AISTATS, March 2007. [4] Kai Yu, Wei Chu, Shipeng Yu, Volker Tresp, and Zhao Xu. Stochastic Relational Models for Discriminative Link Prediction. In NIPS 19, Cambridge, MA, 2007. MIT Press. [5] Yee Whye Teh, Matthias Seeger, and <strong>Michael</strong> I. Jordan. Semiparametric latent factor models. In Proceedings of the 10th AISTATS, pages 333?340, January 2005. [6] Hao Zhang. Maximum-likelihood estimation for multivariate spatial linear coregionalization models. Environmetrics, 18(2):125?...</p>
  836. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div>
  837. </div>
  838.  
  839. <div class="result-row">
  840. <h5 style="width: 80%;"><strong id="result_index">87</strong> Automatic Variational Inference in Stan</h5>
  841. <p style="float: right; margin-top: -40px; color: lightgray;">0.064129524</p>
  842. <h6><strong id="year">2015</strong> - <a href="/search?q=authors:%22David Blei%22">David Blei</a>, <a href="/search?q=authors:%22Alp Kucukelbir%22">Alp Kucukelbir</a>, <a href="/search?q=authors:%22Rajesh Ranganath%22">Rajesh Ranganath</a>, <a href="/search?q=authors:%22Andrew Gelman%22">Andrew Gelman</a></h6>
  843. <p class="light">... IIS-1247664, IIS-1009542, SES-1424962, ONR N00014-11-1-0651, DARPA FA8750-14-2-0009, N66001-15-C-4032, Sloan G-2015-13987, IES DE R305D140059, NDSEG, Facebook, Adobe, Amazon, and the Siebel Scholar and John Templeton Foundations. 8 References [1] <strong>Michael</strong> I Jordan, Zoubin Ghahramani, Tommi S Jaakkola, and Lawrence K Saul. An introduction to variational methods for graphical models. Machine Learning, 37(2):183?233, 1999. [2] Martin J Wainwright and <strong>Michael</strong> I Jordan. Graphical models, exponentia...</p>
  844. <div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  845. </div>
  846.  
  847. <div class="result-row">
  848. <h5 style="width: 80%;"><strong id="result_index">88</strong> FACTORIE: Probabilistic Programming via Imperatively Defined Factor Graphs</h5>
  849. <p style="float: right; margin-top: -40px; color: lightgray;">0.063254446</p>
  850. <h6><strong id="year">2009</strong> - <a href="/search?q=authors:%22Andrew McCallum%22">Andrew McCallum</a>, <a href="/search?q=authors:%22Karl Schultz%22">Karl Schultz</a>, <a href="/search?q=authors:%22Sameer Singh%22">Sameer Singh</a></h6>
  851. <p class="light">...is, University of Massachusetts, 2008. [18] Charles Sutton and Andrew McCallum. Collective segmentation and labeling of distant entities in information extraction. Technical Report TR#04-49, University of Massachusetts, July 2004. [19] Aron Culotta, <strong>Michael</strong> Wick, and Andrew McCallum. First-order probabilistic models for coreference resolution. In NAACL: Human Language Technologies (NAACL/HLT), 2007. [20] Khashayar Rohanimanesh, <strong>Michael</strong> Wick, and Andrew McCallum. Inference and learning in large f...</p>
  852. <div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2214%22">Topic 14 &lt;model variable algorithm...&gt;</a></div>
  853. </div>
  854.  
  855. <div class="result-row">
  856. <h5 style="width: 80%;"><strong id="result_index">89</strong> Projection Retrieval for Classification</h5>
  857. <p style="float: right; margin-top: -40px; color: lightgray;">0.06282194</p>
  858. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Artur Dubrawski%22">Artur Dubrawski</a>, <a href="/search?q=authors:%22Madalina Fiterau%22">Madalina Fiterau</a></h6>
  859. <p class="light">...rocess. Acknowledgments This material is based upon work supported by the NSF, under Grant No. IIS-0911032. 8 References [1] Mark W. Craven and Jude W. Shavlik. Extracting Tree-Structured Representations of Trained Networks. In David S. Touretzky, <strong>Michael</strong> C. Mozer, and <strong>Michael</strong> E. Hasselmo, editors, Advances in Neural Information Processing Systems, volume 8, pages 24?30. The MIT Press, 1996. [2] Pedro Domingos. Knowledge discovery via multiple models. Intelligent Data Analysis, 2:187?202, 1998...</p>
  860. <div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div>
  861. </div>
  862.  
  863. <div class="result-row">
  864. <h5 style="width: 80%;"><strong id="result_index">90</strong> Closed-Form Inversion of Backpropagation Networks: Theory and Optimization Issues</h5>
  865. <p style="float: right; margin-top: -40px; color: lightgray;">0.061915796</p>
  866. <h6><strong id="year">1990</strong> - <a href="/search?q=authors:%22Michael L. Rossen%22">Michael L. Rossen</a></h6>
  867. <p class="light">Closed-Form Inversion of Backpropagation Networks: Theory and Optimization Issues <strong>Michael</strong> L. Rossen HNC, Inc. 5.501 Oberlin Drive San Diego, CA 92121 rossen@amos.ucsd.edu Abstract We describe a closed-form technique for mapping the output of a trained backpropagation network int.o input activity space. The mapping is an inverse m...</p>
  868. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2217%22">Topic 17 &lt;image sparse filter learn...&gt;</a></div>
  869. </div>
  870.  
  871. <div class="result-row">
  872. <h5 style="width: 80%;"><strong id="result_index">91</strong> Regularized Spectral Clustering under the Degree-Corrected Stochastic Blockmodel</h5>
  873. <p style="float: right; margin-top: -40px; color: lightgray;">0.061817847</p>
  874. <h6><strong id="year">2013</strong> - <a href="/search?q=authors:%22Tai Qin%22">Tai Qin</a>, <a href="/search?q=authors:%22Karl Rohe%22">Karl Rohe</a></h6>
  875. <p class="light">...] P.W. Holland and S. Leinhardt. Stochastic blockmodels: First steps. Social networks, 5(2): 109?137, 1983. [10] Brian Karrer and Mark EJ Newman. Stochastic blockmodels and community structure in networks. Physical Review E, 83(1):016107, 2011. [11] <strong>Michael</strong> W Mahoney. Randomized algorithms for matrices and data. Advances in Machine Learning and Data Mining for Astronomy, CRC Press, Taylor &amp; Francis Group, Eds.: <strong>Michael</strong> J. Way, Jeffrey D. Scargle, Kamal M. Ali, Ashok N. Srivastava, p. 647-672, 1:...</p>
  876. <div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div>
  877. </div>
  878.  
  879. <div class="result-row">
  880. <h5 style="width: 80%;"><strong id="result_index">92</strong> An Efficient Implementation of the Back-propagation Algorithm on the Connection Machine CM-2</h5>
  881. <p style="float: right; margin-top: -40px; color: lightgray;">0.060244728</p>
  882. <h6><strong id="year">1989</strong> - <a href="/search?q=authors:%22Xiru Zhang%22">Xiru Zhang</a>, <a href="/search?q=authors:%22Michael McKenna%22">Michael McKenna</a>, <a href="/search?q=authors:%22Jill P. Mesirov%22">Jill P. Mesirov</a>, <a href="/search?q=authors:%22David L. Waltz%22">David L. Waltz</a></h6>
  883. <p class="light">An Efficient Implementation of the Back-propagation Algorithm A n Efficient Implementation of the Back-propagation Algorithm on the Connection Machine CM-2 Xiru Zhang! <strong>Michael</strong> Mckenna Jill P. Mesirov David L. Waltz Thinking Machines Corporation 245 First Street, Cambridge, MA 02142-1214 ABSTRACT In this paper, we present a novel implementation of the widely used Back-propagation neural net learning algorithm on...</p>
  884. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div>
  885. </div>
  886.  
  887. <div class="result-row">
  888. <h5 style="width: 80%;"><strong id="result_index">93</strong> On Strategy Stitching in Large Extensive Form Multiplayer Games</h5>
  889. <p style="float: right; margin-top: -40px; color: lightgray;">0.05938743</p>
  890. <h6><strong id="year">2011</strong> - <a href="/search?q=authors:%22Richard G. Gibson%22">Richard G. Gibson</a>, <a href="/search?q=authors:%22Duane Szafron%22">Duane Szafron</a></h6>
  891. <p class="light">...N. Bard. Strategy grafting in extensive games. In NIPS-22, pages 2026?2034, 2009. [12] K. Waugh, D. Schnizlein, M. Bowling, and D. Szafron. Abstraction pathologies in extensive games. In SARA, pages 781?788, 2009. [13] Kevin Waugh, Martin Zinkevich, <strong>Michael</strong> Johanson, Morgan Kan, David Schnizlein, and <strong>Michael</strong> Bowling. A practical use of imperfect recall. In SARA, pages 175?182, 2009. [14] M. Zinkevich, M. Johanson, M. Bowling, and C. Piccione. Regret minimization in games with incomplete informat...</p>
  892. <div class="chip"><a href="/search?q=topic:%2216%22">Topic 16 &lt;query user item rank set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2211%22">Topic 11 &lt;algorithm regret bandit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div>
  893. </div>
  894.  
  895. <div class="result-row">
  896. <h5 style="width: 80%;"><strong id="result_index">94</strong> Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress</h5>
  897. <p style="float: right; margin-top: -40px; color: lightgray;">0.05863927</p>
  898. <h6><strong id="year">2012</strong> - <a href="/search?q=authors:%22Marc Toussaint%22">Marc Toussaint</a>, <a href="/search?q=authors:%22Manuel Lopes%22">Manuel Lopes</a>, <a href="/search?q=authors:%22Tobias Lang%22">Tobias Lang</a>, <a href="/search?q=authors:%22Pierre-yves Oudeyer%22">Pierre-yves Oudeyer</a></h6>
  899. <p class="light">... for a developing curious agent. In AAMAS Workshop on Adaptive Learning Agents (ALA), 2012. [7] Sham Kakade. On the Sample Complexity of Reinforcement Learning. PhD thesis, Gatsby Computational Neuroscience Unit, University College London, 2003. [8] <strong>Michael</strong> Kearns and Satinder Singh. Near-optimal reinforcement learning in polynomial time. Machine Learning Journal, 49(2-3):209?232, 2002. [9] J. Zico Kolter and Andrew Ng. Near-Bayesian exploration in polynomial time. In Int. Conf. on Machine Learn...</p>
  900. <div class="chip"><a href="/search?q=topic:%2220%22">Topic 20 &lt;state policy action...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div>
  901. </div>
  902.  
  903. <div class="result-row">
  904. <h5 style="width: 80%;"><strong id="result_index">95</strong> Fast and Accurate k-means For Large Datasets</h5>
  905. <p style="float: right; margin-top: -40px; color: lightgray;">0.05863927</p>
  906. <h6><strong id="year">2011</strong> - <a href="/search?q=authors:%22Michael Shindler%22">Michael Shindler</a>, <a href="/search?q=authors:%22Alex Wong%22">Alex Wong</a>, <a href="/search?q=authors:%22Adam W. Meyerson%22">Adam W. Meyerson</a></h6>
  907. <p class="light">Fast and Accurate k-llleans For Large Datasets <strong>Michael</strong> Shindler School of EECS Oregon State University shindler@eecs.oregonstate.edu Alex Wong Department of Computer Science UC Los Angeles alexw@seas.ucla.edu Adam Meyerson Google, Inc. Mountain View, CA awmeyerson@google.com Abstract Clusterin...</p>
  908. <div class="chip"><a href="/search?q=topic:%2221%22">Topic 21 &lt;algorithm gradient time...&gt;</a></div><div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2223%22">Topic 23 &lt;problem algorithm function...&gt;</a></div>
  909. </div>
  910.  
  911. <div class="result-row">
  912. <h5 style="width: 80%;"><strong id="result_index">96</strong> The Hopfield Model with Multi-Level Neurons</h5>
  913. <p style="float: right; margin-top: -40px; color: lightgray;">0.055049527</p>
  914. <h6><strong id="year">1987</strong> - <a href="/search?q=authors:%22Michael Fleisher%22">Michael Fleisher</a></h6>
  915. <p class="light">278 THE HOPFIELD MODEL WITH MULTI-LEVEL NEURONS <strong>Michael</strong> Fleisher Department of Electrical Engineering Technion - Israel Institute of Technology Haifa 32000, Israel ABSTRACT The Hopfield neural network. model for associative memory is generalized. The generalization replaces two state neurons by ...</p>
  916. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2212%22">Topic 12 &lt;bound theorem function let...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2218%22">Topic 18 &lt;neuron spike time input...&gt;</a></div>
  917. </div>
  918.  
  919. <div class="result-row">
  920. <h5 style="width: 80%;"><strong id="result_index">97</strong> Lifted Inference Seen from the Other Side : The Tractable Features</h5>
  921. <p style="float: right; margin-top: -40px; color: lightgray;">0.053233713</p>
  922. <h6><strong id="year">2010</strong> - <a href="/search?q=authors:%22Vibhav Gogate%22">Vibhav Gogate</a>, <a href="/search?q=authors:%22Abhay Jha%22">Abhay Jha</a>, <a href="/search?q=authors:%22Alexandra Meliou%22">Alexandra Meliou</a>, <a href="/search?q=authors:%22Dan Suciu%22">Dan Suciu</a></h6>
  923. <p class="light">...listic inference. In IJCAI?05: Proceedings of the 19th international joint conference on Artificial intelligence, pages 1319?1325, San Francisco, CA, USA, 2005. Morgan Kaufmann Publishers Inc. [6] Brian Milch, Luke S. Zettlemoyer, Kristian Kersting, <strong>Michael</strong> Haimes, and Leslie Pack Kaelbling. Lifted probabilistic inference with counting formulas. In AAAI?08: Proceedings of the 23rd national conference on Artificial intelligence, pages 1062?1068. AAAI Press, 2008. [7] K. S. Ng, J. W. Lloyd, and W....</p>
  924. <div class="chip"><a href="/search?q=topic:%222%22">Topic 2 &lt;graph node tree edge set...&gt;</a></div><div class="chip"><a href="/search?q=topic:%224%22">Topic 4 &lt;kernel matrix regression...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2219%22">Topic 19 &lt;model word topic document...&gt;</a></div>
  925. </div>
  926.  
  927. <div class="result-row">
  928. <h5 style="width: 80%;"><strong id="result_index">98</strong> Learning the k in k-means</h5>
  929. <p style="float: right; margin-top: -40px; color: lightgray;">0.053233713</p>
  930. <h6><strong id="year">2003</strong> - <a href="/search?q=authors:%22Greg Hamerly%22">Greg Hamerly</a>, <a href="/search?q=authors:%22Charles Elkan%22">Charles Elkan</a></h6>
  931. <p class="light">...puting Surveys, 31(3):264?323, 1999. [10] Robert E. Kass and Larry Wasserman. A reference Bayesian test for nested hypotheses and its relationship to the Schwarz criterion. Journal of the American Statistical Association, 90(431):928?934, 1995. [11] <strong>Michael</strong> J. Kearns, Yishay Mansour, Andrew Y. Ng, and Dana Ron. An experimental and theoretical comparison of model selection methods. In Computational Learing Theory (COLT), pages 21?30, 1995. [12] Yann LeCun, L?eon Bottou, Yoshua Bengio, and Patrick...</p>
  932. <div class="chip"><a href="/search?q=topic:%220%22">Topic 0 &lt;matrix cluster point datum...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2224%22">Topic 24 &lt;model distribution...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2210%22">Topic 10 &lt;feature label training...&gt;</a></div>
  933. </div>
  934.  
  935. <div class="result-row">
  936. <h5 style="width: 80%;"><strong id="result_index">99</strong> A Self-organizing Associative Memory System for Control Applications</h5>
  937. <p style="float: right; margin-top: -40px; color: lightgray;">0.05309942</p>
  938. <h6><strong id="year">1989</strong> - <a href="/search?q=authors:%22Michael Hormel%22">Michael Hormel</a></h6>
  939. <p class="light">332 Hormel A Sell-organizing Associative Memory System lor Control Applications <strong>Michael</strong> Bormel Department of Control Theory and Robotics Technical University of Darmstadt Schlossgraben 1 6100 Darmstadt/W.-Ger.any ABSTRACT The CHAC storage scheme has been used as a basis for a software implementation of an associative .emory sys...</p>
  940. <div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div><div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%223%22">Topic 3 &lt;cell response model...&gt;</a></div>
  941. </div>
  942.  
  943. <div class="result-row">
  944. <h5 style="width: 80%;"><strong id="result_index">100</strong> Cycles: A Simulation Tool for Studying Cyclic Neural Networks</h5>
  945. <p style="float: right; margin-top: -40px; color: lightgray;">0.053070683</p>
  946. <h6><strong id="year">1987</strong> - <a href="/search?q=authors:%22Michael T. Gately%22">Michael T. Gately</a></h6>
  947. <p class="light">290 CYCLES: A Simulation Tool for Studying Cyclic Neural Networks <strong>Michael</strong> T. Gately Texas Instruments Incorporated, Dallas, TX 75265 ABSTRACT A computer program has been designed and implemented to allow a researcher to analyze the oscillatory behavior of simulated neural networks with cyclic connectivity. The comp...</p>
  948. <div class="chip"><a href="/search?q=topic:%2213%22">Topic 13 &lt;network memory pattern...&gt;</a></div><div class="chip"><a href="/search?q=topic:%228%22">Topic 8 &lt;model time dynamic state...&gt;</a></div><div class="chip"><a href="/search?q=topic:%226%22">Topic 6 &lt;network input weight unit...&gt;</a></div>
  949. </div>
  950.  
  951.  
  952.  
  953. <!-- Render Results using JavaScript -->
  954. <script>
  955. /*
  956. // Get results from API.
  957.  
  958. // Do some cleaning of the result string. TODO: Make this nicer.
  959. results = results.replace(/'/g, '');
  960. results = results.replace(/[\0\x08\x09\x1a|&;$\f%@<>()+]/g, "");
  961. results = results.replace(/[\u0000-\u0019]+/g,"");
  962. results = results.replace(/\\/g, '');
  963. // Parse as JSON Object.
  964. var results_json = JSON.parse(results);
  965.  
  966. // Loop through results, write each JSON object as HTML.
  967. for (var i = 0; i < results_json["result_count"][0]; i++){
  968. document.write('<div class="result-row">');
  969.  
  970. // Gets the event type. If the event type is not specified, it is a paper.
  971. // TODO: check if this is actually true.
  972. var event_type = results_json["results"][i]["event_type"][0];
  973. if(event_type == ""){
  974. event_type = "Paper";
  975. }
  976. // Get the text fragment and make the first query word bold for aesthetic reasons.
  977. var text_fragment = results_json["results"][i]["text_fragment"][0];
  978. text_fragment = text_fragment.replace(results_json["query"][0], '<strong>'+results_json["query"][0]+'</strong>');
  979.  
  980. // Render the title and its index.
  981. document.write('<h5 style="width: 80%;"><strong id="result_index">'+(i+1)+'. </strong>'+results_json["results"][i]["title"][0]+'</h5>');
  982.  
  983. // Render the score the Lucene scorer returned.
  984. document.write('<p style="float: right; margin-top: -40px; color: lightgray;">'+results_json["results"][i]["score"][0]+'</p>');
  985.  
  986. // Write the year of publishing, authors and event type.
  987. document.write('<h6><strong id="year">'+results_json["results"][i]["year"][0]+'</strong> - '+event_type+' - <a href="">'+results_json["results"][i]["authors"][0]+ '</a></h6>');
  988.  
  989. // Write the text fragment.
  990. document.write('<p class="light">'+text_fragment+'</p>');
  991.  
  992. // TODO: Implement rendering of topic when API provides the topics for each document.
  993. document.write(' <div class="chip">Topic1 </div><div class="chip">Topic2 </div><div class="chip">Topic3</div>');
  994.  
  995. // Close the div and add a line.
  996. document.write('</div>');
  997. document.write('<hr>');
  998. }
  999.  
  1000. // If the API returns no results, show this to the user.
  1001. if(results_json["result_count"][0] == "0"){
  1002. document.write("<center><h4 style='color: lightgray;'>No results found.</h4></center>");
  1003. }
  1004. */
  1005.  
  1006. </script>
  1007. </div>
  1008. </div>
  1009. </div>
  1010.  
  1011. <br><br>
  1012. <div>
  1013. <center>
  1014. <hr>
  1015. <a href="/">Querying</a> - <a href="/author-influence">Author Influence</a> - <a href="/topic-evolution">Topic Evolution</a>
  1016. </center>
  1017. </div>
  1018. <br>
  1019. </div>
  1020. <!-- Scripts -->
  1021. <script src="https://code.jquery.com/jquery-2.1.1.min.js"></script>
  1022. <script src="/static/materialize/js/materialize.js"></script>
  1023. <!--<script src="/static/js/init.js"></script>-->
  1024. <script>
  1025.  
  1026. </script>
  1027. </body>
  1028. </html>
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!