Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- function [J grad] = nnCostFunction(nn_params, ...
- input_layer_size, ...
- hidden_layer_size, ...
- num_labels, ...
- X, y, lambda)
- Theta1 = reshape(nn_params(1:hidden_layer_size * (input_layer_size + 1)), ...
- hidden_layer_size, (input_layer_size + 1));
- Theta2 = reshape(nn_params((1 + (hidden_layer_size * (input_layer_size + 1))):end), ...
- num_labels, (hidden_layer_size + 1));
- % Setup some useful variables
- m = size(X, 1);
- X = [ones(m,1) X];
- % You need to return the following variables correctly
- J = 0;
- Theta1_grad = zeros(size(Theta1));
- Theta2_grad = zeros(size(Theta2));
- % ====================== YOUR CODE HERE ======================
- % Instructions: You should complete the code by working through the
- % following parts.
- %
- % Part 1: Feedforward the neural network and return the cost in the
- % variable J. After implementing Part 1, you can verify that your
- % cost function computation is correct by verifying the cost
- % computed in ex4.m
- %
- % Part 2: Implement the backpropagation algorithm to compute the gradients
- % Theta1_grad and Theta2_grad. You should return the partial derivatives of
- % the cost function with respect to Theta1 and Theta2 in Theta1_grad and
- % Theta2_grad, respectively. After implementing Part 2, you can check
- % that your implementation is correct by running checkNNGradients
- %
- % Note: The vector y passed into the function is a vector of labels
- % containing values from 1..K. You need to map this vector into a
- % binary vector of 1's and 0's to be used with the neural network
- % cost function.
- %
- % Hint: We recommend implementing backpropagation using a for-loop
- % over the training examples if you are implementing it for the
- % first time.
- %
- % Part 3: Implement regularization with the cost function and gradients.
- %
- % Hint: You can implement this around the code for
- % backpropagation. That is, you can compute the gradients for
- % the regularization separately and then add them to Theta1_grad
- % and Theta2_grad from Part 2.
- %
- h1_out = reshape([ones(m,1) sigmoid(X * Theta1')], m, size(Theta1,1) + 1);
- h = sigmoid(h1_out * Theta2');
- tmp_y = zeros(size(h));
- for i = 1:m,
- tmp_y(i,y(i)) = 1;
- end
- y = tmp_y;
- tmp_theta1 = Theta1;
- tmp_theta2 = Theta2;
- tmp_theta1(:,1) = 0;
- tmp_theta2(:,1) = 0;
- J = (-1/m)*sum(sum(y.*log(h)) + sum((1-y).*log(1 - h))) + ...
- (lambda/(2*m))*(sum(tmp_theta1(:) .^ 2) + sum(tmp_theta2(:) .^ 2));
- a_1 = X;
- z_2 = a_1 * Theta1';
- a_2 = h1_out;
- z_3 = h1_out * Theta2';
- a_3 = h;
- diff_3 = a_3 - y;
- diff_2 = diff_3 * Theta2 .* sigmoidGradient([ones(size(z_2, 1), 1) z_2]);
- diff_2 = diff_2(:,2:end);
- delta_1 = diff_2' * a_1;
- delta_2 = diff_3' * a_2;
- Theta1_grad = delta_1 ./ m + (lambda/m) .* tmp_theta1;
- Theta2_grad = delta_2 ./ m + (lambda/m) .* tmp_theta2;
- % =========================================================================
- % Unroll gradients
- grad = [Theta1_grad(:) ; Theta2_grad(:)];
- end
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement