View difference between Paste ID: x7qvT6Kh and gwYBZjZ8

- def train(self, training_set_inputs, training_set_outputs):
+def train(self, training_set_inputs, training_set_outputs):
-
+    for i in range(100):
-        for i in range(100):
+        self.train_global_step(training_set_inputs, training_set_outputs)
-            self.train_global_step(training_set_inputs, training_set_outputs)
+        if self.layer2_error < 0.1:
-            if (self.layer2_error) < 0.1:
+            break
-                break
+
 def train_global_step(self, training_set_inputs, training_set_outputs):
-
+    self.layer2_error = 0
-    def train_global_step(self, training_set_inputs, training_set_outputs):
+    self.learning_rate = 0.1
-
+
-            self.layer2_error = 0
+    for iteration in range(len(training_set_inputs)):
-            self.learning_rate = 0.1
+        # Pass the training set through our neural network
         output_from_layer_1, output_from_layer_2 = self.think(training_set_inputs)
-            for iteration in range(len(training_set_inputs)):
+
-                    # Pass the training set through our neural network
+        # Calculate the error for layer 2 (The difference between the desired output
-                output_from_layer_1, output_from_layer_2 = self.think(training_set_inputs)
+        # and the predicted output).
         layer2_error = training_set_outputs - output_from_layer_2
-                            # Calculate the error for layer 2 (The difference between the desired output
+        layer2_delta = layer2_error * self.__sigmoid_derivative(output_from_layer_2)
-                            # and the predicted output).
+
-                layer2_error = training_set_outputs - output_from_layer_2
+        # Calculate the error for layer 1 (By looking at the weights in layer 1,
-                layer2_delta = layer2_error * self.__sigmoid_derivative(output_from_layer_2)
+        # we can determine by how much layer 1 contributed to the error in layer 2).
         layer1_error = layer2_delta.dot(self.layer2.synaptic_weights.T)
-                            # Calculate the error for layer 1 (By looking at the weights in layer 1,
+        layer1_delta = layer1_error * self.__sigmoid_derivative(output_from_layer_1)
-                            # we can determine by how much layer 1 contributed to the error in layer 2).
+
-                layer1_error = layer2_delta.dot(self.layer2.synaptic_weights.T)
+        # Calculate how much to adjust the weights by
-                layer1_delta = layer1_error * self.__sigmoid_derivative(output_from_layer_1)
+        layer1_adjustment = training_set_inputs.T.dot(layer1_delta)
         layer2_adjustment = output_from_layer_1.T.dot(layer2_delta)
-                            # Calculate how much to adjust the weights by
+
-                layer1_adjustment = training_set_inputs.T.dot(layer1_delta)
+        # Adjust the weights.
-                layer2_adjustment = output_from_layer_1.T.dot(layer2_delta)
+        self.layer1.synaptic_weights += self.learning_rate*layer1_adjustment
         self.layer2.synaptic_weights += self.learning_rate*layer2_adjustment