1. 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
2. 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 first column 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 column of W corresponds to the parameters for the bias unit
%
epsilon_init = 0.12;
W = rand(L_out, 1+L_in) * epsilon_init * 2 - epsilon_init;
% =========================================================================
end
3. 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];
z2 = X * Theta1';
a2 = sigmoid(z2);
z3 = [ones(m,1) a2];
h = sigmoid(z3 * Theta2');
yk = zeros(m,num_labels); %数据中的y是数,需要构造一个向量来对应10个神经元的输出
for i = 1:m
yk(i,y(i)) = 1; %yk为向量,其中数据对应的元素为1,其余为0
end
J = -(1/m) * sum(sum(yk .* log(h) + (1-yk) .* log(1-h))); %如果直接用矩阵乘法,会导致第i个数据与第j个数据估值相乘的错误(i!=j),点乘就直接把每一次预测数据对应起来了
% 正则化时不需要偏置项的参数
Theta1_reg = Theta1(:,2:end);
Theta2_reg = Theta2(:,2:end);
J = J + lambda/(2*m) * (sum(sum(Theta1_reg .* Theta1_reg)) + sum(sum(Theta2_reg .* Theta2_reg)));
for i = 1:m
z_2 = X(i,:) * Theta1'; %X是行向量
a_2 = sigmoid(z_2);
z_3 = [1 a_2] * Theta2';
a_3 = sigmoid(z_3);
yk = zeros(num_labels,1);
yk(y(i),1) = 1;
delta_3 = a_3' - yk;
delta_2 = Theta2' * delta_3 .* sigmoidGradient([1 z_2]');
delta_2 = delta_2(2:end);
Theta1_grad = Theta1_grad + delta_2 * X(i,:);
Theta2_grad = Theta2_grad + delta_3 * [1 a_2];
end
Theta1_grad(:,1)=Theta1_grad(:,1)/m; %偏置项不需要正则化
Theta1_grad(:,2:size(Theta1_grad,2))=Theta1_grad(:,2:size(Theta1_grad,2))/m + lambda*Theta1(:,2:size(Theta1,2))/m;
Theta2_grad(:,1)=Theta2_grad(:,1)/m; %偏置项不需要正则化
Theta2_grad(:,2:size(Theta2_grad,2))=Theta2_grad(:,2:size(Theta2_grad,2))/m + lambda*Theta2(:,2:size(Theta2,2))/m;
% -------------------------------------------------------------
% =========================================================================
% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end