1.灵活应用矩阵运算代替for循环的冗余
2.当使用后向传播时 每次运算一个样本 先计算其feedforward 求出J 再求出最后一层的delta差 以此进行后向传播以得到代价函数J关于每一个权重theta的导数
3.计算正则化后的代价函数,注意不要加上theta0的平方项
4. 利用δ 反求 △时,△(l)=△(l)+δ(l+1)*a(l)
注意skep or remove θ0 (可以先求 后skip 也可以如本文一样 先不求)
==========================================================================
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);% number of samples
% 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.
%
% my_code===========part 1 feedforward=====================
a1 = [ones(m, 1) X];
z2 = a1 * Theta1';
a2 = sigmoid(z2);
a2 = [ones(m, 1) a2];
z3 = a2 * Theta2';
h = sigmoid(z3);
%calculate yk
yk = zeros(m, num_labels);
for i = 1:m
yk(i, y(i)) = 1; %y is class vector
end
%costFunction
J = (1/m)* sum(sum(((-yk) .* log(h) - (1 - yk) .* log(1 - h))));
%=========================part 2 regularization============
Theta1_new=Theta1(:,2:size(Theta1,2));
Theta2_new=Theta2(:,2:size(Theta2,2));
J=J+lambda/2/m*( sum(sum(Theta1_new.*Theta1_new))+sum(sum(Theta2_new.*Theta2_new)));
%=========================part 3 backpropagation=======================
Delta_1=zeros(hidden_layer_size,input_layer_size+1);
Delta_2=zeros(num_labels,hidden_layer_size+1);
for t=1:m
a1=[1 X(t,:)]; %1*401
z2=a1*Theta1'; %1*25
a2=sigmoid(z2); %1*25
a2_plus=[1 a2]; %1*26
z3=a2_plus*Theta2'; %1*10
a3=sigmoid(z3);
delta_3=a3-yk(t,:); %1*10
delta_2=Theta2(:,2:end)'*delta_3'.*sigmoidGradient(z2'); %25*1
Delta_1=Delta_1+delta_2*a1; %25*401
Delta_2=Delta_2+delta_3'*a2_plus; %10*26
end
Theta1_grad=1/m*Delta_1;
Theta2_grad=1/m*Delta_2;
Theta1_grad(:,2:end)=Theta1_grad(:,2:end)+lambda/m*Theta1(:,2:end);
Theta2_grad(:,2:end)=Theta2_grad(:,2:end)+lambda/m*Theta2(:,2:end);
% -------------------------------------------------------------
% =========================================================================
% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end