130 lines
4.0 KiB
Matlab
130 lines
4.0 KiB
Matlab
function [J grad] = nnCostFunction(nn_params, ...
|
|
input_layer_size, ...
|
|
hidden_layer_size, ...
|
|
num_labels, ...
|
|
X, y, lambda)
|
|
%NNCOSTFUNCTION Implements the neural network cost function for a two layer
|
|
%neural network which performs classification
|
|
% [J grad] = NNCOSTFUNCTON(nn_params, hidden_layer_size, num_labels, ...
|
|
% X, y, lambda) computes the cost and gradient of the neural network. The
|
|
% parameters for the neural network are "unrolled" into the vector
|
|
% nn_params and need to be converted back into the weight matrices.
|
|
%
|
|
% The returned parameter grad should be a "unrolled" vector of the
|
|
% partial derivatives of the neural network.
|
|
%
|
|
|
|
% Reshape nn_params back into the parameters Theta1 and Theta2, the weight matrices
|
|
% for our 2 layer neural network
|
|
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);
|
|
|
|
% 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.
|
|
%
|
|
|
|
|
|
%
|
|
% Activations ....
|
|
%
|
|
a1 = [ones(m, 1) X];
|
|
a2 = [ones(m,1) sigmoid(a1*Theta1')];
|
|
a3 = sigmoid(a2*Theta2');
|
|
h = a3;
|
|
|
|
%
|
|
% Transform y to .....
|
|
%
|
|
Y = zeros(m,num_labels);
|
|
for i=1:m,
|
|
Y(i,y(i))=1;
|
|
end
|
|
|
|
%
|
|
% This is the J without ....
|
|
%
|
|
J = sum(sum( Y .* log(h) .+ (1-Y) .* log(1-h) )) / (-m);
|
|
J = J + (lambda/(2*m))*sum(sum(Theta1(:,2:size(Theta1,2)).^2));
|
|
J = J + (lambda/(2*m))*sum(sum(Theta2(:,2:size(Theta2,2)).^2));
|
|
|
|
%
|
|
% Gradient ....
|
|
%
|
|
d3 = a3 .- Y;
|
|
d2 = d3 * Theta2 .* (a2.*(1-a2));
|
|
|
|
dlt1 = zeros(size(Theta1));
|
|
dlt2 = zeros(size(Theta2));
|
|
for i=1:m,
|
|
dlt2 = dlt2 + d3(i,:)'*a2(i,:);
|
|
t = d2(i,:)'*a1(i,:);
|
|
t = t(2:size(t,1),:);
|
|
dlt1 = dlt1 + t;
|
|
end
|
|
|
|
Theta1_grad = dlt1/m;
|
|
Theta2_grad = dlt2/m;
|
|
|
|
%
|
|
% Regularization ....
|
|
%
|
|
r1 = lambda*Theta1/m;
|
|
r2 = lambda*Theta2/m;
|
|
|
|
t1s = size(Theta1);
|
|
r1 = [ zeros(t1s(1),1) r1(:,2:t1s(2))];
|
|
|
|
t2s = size(Theta2);
|
|
r2 = [ zeros(t2s(1),1) r2(:,2:t2s(2))];
|
|
|
|
Theta1_grad = Theta1_grad + r1;
|
|
Theta2_grad = Theta2_grad + r2;
|
|
|
|
|
|
% =========================================================================
|
|
|
|
% Unroll gradients
|
|
grad = [Theta1_grad(:) ; Theta2_grad(:)];
|
|
|
|
|
|
end
|