The step of this exercise is show in the pdf which i have updoaded.
Neural network of this exercise is not easy to finish,okay,let me show U.
nnCostFunction:
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.
%
%=================================Costfunction========================================
X=[ones(size(X,1),1) X];
a1=X;
z2=Theta1*a1';
a2=sigmoid(z2);
a2=[ones(1,m) ; a2];
z3=Theta2*a2;
a3=sigmoid(z3);
y_vec=zeros(num_labels,m);
for index=1:m
y_vec(y(index),index)=1;
end
size(y_vec);
for index_num=1:m
J+= sum(-1*y_vec(:,index_num).*log(a3(:,index_num))-(1-y_vec(:,index_num)).*log(1-a3(:,index_num)));
end
J=J/m;
size(J);
J=J+(lambda/( 2*m )) * (sum (sum ( Theta1(:,2:end).^2 ) )+ sum(sum(Theta2(:,2:end).^2)) )
%===================================backprogation=======================================
%Delta2=(zeros(size(Theta2))) (:,2:end);
%Delta1=(zeros(size(Theta1))) (:,2:end);
%for ind=1:m
% delta3=a3(:,ind)-y_vec(:,ind);
% delta2=sum( (Theta2'*delta3)(2:end).*sigmoidGradient(z2(:,ind)),2 );
% Delta2=Delta2 + delta3*a2(2:end,ind)';
% test=delta2*a1(ind,2:end);
% Delta1=Delta1 + delta2*a1(ind,2:end);
%end
Delta1 = zeros( hidden_layer_size, (input_layer_size + 1));
Delta2 = zeros( num_labels, (hidden_layer_size + 1));
%Delta需要bias unit,delta不需要bias unit
for i=1:m
delta3 = a3(:,i) - y_vec(:,i);
#注意这里的δ是不包含bias unit的delta的,毕竟bias unit永远是1,
#不需要计算delta, 下面的2:end,: 过滤掉了bias unit相关值
delta2 = (Theta2'*delta3)(2:end,:).*sigmoidGradient(z2(:,i));
#移除bias unit上的delta2,但是由于上面sigmoidGradient式子中
#的z,本身不包含bias unit,所以下面的过滤不必要,注释掉。
#delta2 = delta2(2:end);
Delta2 += delta3 * a2(:,i)';
#第一层的input是一行一行的,和后面的结构不一样,后面是一列作为一个example
Delta1 += delta2 * a1(i,:);
end
Theta1_grad=Delta1/m;
Theta2_grad=Delta2/m;
Theta2_grad(:,2:end) = Theta2_grad(:,2:end) .+ lambda * Theta2(:,2:end) / m;
Theta1_grad(:,2:end) = Theta1_grad(:,2:end) .+ lambda * Theta1(:,2:end) / m;
% =========================================================================
% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];
%训练集一个一个轮流训练,一次只训练一个set,前进后反向。
end
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=( 1.0 ./ (1.0 .+ exp(-z)) ) *( (1.0 .- (1.0 ./ (1.0 .+ exp(-z)) ) )' );
g=sigmoid(z).*(1-sigmoid(z));
randomInitializeWeights:
function W = randInitializeWeights(L_in, L_out)
%RANDINITIALIZEWEIGHTS Randomly initialize the weights of a layer with L_in
%incoming connections and L_out outgoing connections
% W = RANDINITIALIZEWEIGHTS(L_in, L_out) randomly initializes the weights
% of a layer with L_in incoming connections and L_out outgoing
% connections.
%
% Note that W should be set to a matrix of size(L_out, 1 + L_in) as
% the column row of W handles the "bias" terms
%
% You need to return the following variables correctly
W = zeros(L_out, 1 + L_in);
% ====================== YOUR CODE HERE ======================
% Instructions: Initialize W randomly so that we break the symmetry while
% training the neural network.
%
% Note: The first row of W corresponds to the parameters for the bias units
%
epsilon_init=0.12;
W=rand(L_out,L_in+1) * 2 * epsilon_init - epsilon_init;
% =========================================================================
end
Tips:
1. some build-in functions in MATLAB must pass a vector of theta,rather than matrix.
2. for y,if U use BP to solve multip-classification problems,then U must change every y to vector.
3. in BP,every single traning set is pass to BP one by one .for the first one,FP using x then BP using y,the second ,third...