ex4

这周重点在back propagation（误差逆传播），具体自己看书还是看课吧，对我来说比较难的还是在矩阵维度经常搞混

nnCostFunction.m

为了避免搞混维度，我后面都标注了以ex4.m里面数据为例的维度供自己参考，在pdf文件中被分为了3个part来指导，part1就是feedforward计算代价函数，part2就是bp算法来推出theta1和theta2的偏导数，part3就是正则化

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));%25*401

Theta2 = reshape(nn_params((1 + (hidden_layer_size * (input_layer_size + 1))):end), ...
                 num_labels, (hidden_layer_size + 1));%10*26

% 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.
%
a1=[ones(m,1),X];%5000*401
z2=Theta1*a1';   %25*5000
a2=[ones(m,1),(sigmoid(z2))'];%5000*26
z3=Theta2*a2';   %10*5000
h=sigmoid(z3);
temp_y=zeros(m,num_labels);
for i=1:m
    temp_y(i,y(i))=1;
end
J=-sum(sum(temp_y.*log(h')+(1-temp_y).*log((1-h)')))/m;
J=J+(lambda/2/m)*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));

delta_3=h'-temp_y;%5000*10
delta_2=Theta2'*delta_3';%26*5000
delta_2=delta_2(2:end,:);%25*5000
delta_2=delta_2.*sigmoidGradient(z2);%25*5000
Theta1_grad=(Theta1_grad+delta_2*a1)/m+lambda/m*Theta1;%25*401
Theta1_grad(:,1)=Theta1_grad(:,1)-lambda/m*Theta1(:,1);
Theta2_grad=(Theta2_grad+delta_3'*a2)/m+lambda/m*Theta2;%10*26
Theta2_grad(:,1)=Theta2_grad(:,1)-lambda/m*Theta2(:,1);
% -------------------------------------------------------------

% =========================================================================

% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];


end

sigmoidGradient.m

这个就很简单，就是求sigmoid函数的导数

function g = sigmoidGradient(z)
%SIGMOIDGRADIENT returns the gradient of the sigmoid function
%evaluated at z
%   g = SIGMOIDGRADIENT(z) computes the gradient of the sigmoid function
%   evaluated at z. This should work regardless if z is a matrix or a
%   vector. In particular, if z is a vector or matrix, you should return
%   the gradient for each element.

g = zeros(size(z));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the gradient of the sigmoid function evaluated at
%               each value of z (z can be a matrix, vector or scalar).

g=sigmoid(z).*(1-sigmoid(z));
% =============================================================
end