sigmoidGradient.m:
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
randInitializeWeights.m:
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
%
init_epsilon = 0.12;
W = rand(L_out, 1 + L_in) * 2 *init_epsilon - init_epsilon;
% =========================================================================
end
nnCostFunction.m:
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.
%
X = [ones(m, 1) X]; %(5000*401) 第一层
z2 = X*Theta1';
a2 = sigmoid(z2);
a2 = [ones(m, 1) a2]; %(5000*26) 第二层
z3 = a2*Theta2';
a3 = sigmoid(z3); %(5000*10) 第三层
%J = -(1/m)*( sum((log(a3'))*y + log(1-a3')*(1-y)) );
for i = 1:m
a33 = (a3(i,:))'; %(10*1) a3中的第i行
p = zeros(num_labels, 1); %(10*1)
p(y(i)) = 1;
J = -(1/m)*( (log(a33'))*p + log(1-a33')*(1-p) ) + J;
%反向传播
fine3 = a33 - p; %(10*1)
a22 = (a2(i,:)); %(1*26) z2中第i行
z22 = (z2(i,:));
fine2 = (Theta2(:,2:end)'*fine3).*(sigmoidGradient(z22))'; %(25*1)
a11 = X(i,:); %(1*401) X中第i行
%计算出X中每行数据对应的代价函数的函数的偏导数
Theta1_grad = Theta1_grad + fine2 * a11; %(25*401)
Theta2_grad = Theta2_grad + fine3 * a22; %(10*26)
end
temp1 = Theta1(:,2:size(Theta1, 2)).^2; %去除Theta1第一列再各项平方
temp2 = Theta2(:,2:size(Theta2, 2)).^2; %去除Theta2第一列
J = J + (lambda/(2*m))*( sum(temp1(:)) + sum(temp2(:)) );
Theta1_grad = Theta1_grad / m; %平均数
Theta2_grad = Theta2_grad / m;
Theta1(:,1) = 0;
Theta2(:,1) = 0;
Theta1_grad = Theta1_grad + lambda/m * Theta1;
Theta2_grad = Theta2_grad + lambda/m * Theta2;
% -------------------------------------------------------------
% =========================================================================
% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end