1.4 nnCostFunction.m
正向传播: J ( θ ) = 1 m ∑ i = 1 m ∑ k = 1 K [ − y k ( i ) l o g ( ( h θ ( x ( i ) ) ) k ) − ( 1 − y k ( i ) ) l o g ( 1 − ( h θ ( x ( i ) ) ) k ) ] + λ 2 m [ ∑ j = 1 25 ∑ k = 1 400 ( θ j , k ( 1 ) ) 2 + ∑ j = 1 10 ∑ k = 1 25 ( θ j , k ( 2 ) ) 2 ] J(\theta)=\frac{1}{m}\sum_{i=1}^m{\sum_{k=1}^K{\left[-y_k^{(i)}log\left((h_\theta(x^{(i)}))_k\right) - (1-y_k^{(i)})log\left(1-(h_\theta(x^{(i)}))_k\right)\right]}}+\frac{\lambda}{2m}\left[\sum_{j=1}^{25}{\sum_{k=1}^{400}{(\theta_{j,k}^{(1)})^2}}+\sum_{j=1}^{10}{\sum_{k=1}^{25}}{(\theta_{j,k}^{(2)})^2}\right] J(θ)=m1i=1∑mk=1∑K[−yk(i)log((hθ(x(i)))k)−(1−yk(i))log(1−(hθ(x(i)))k)]+2mλ[j=1∑25k=1∑400(θj,k(1))2+j=1∑10k=1∑25(θj,k(2))2]
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.
%
% Feedforward and cost function
layer1 = [ones(m, 1) X];
z2 = layer1*Theta1';
layer2 = sigmoid(z2);
layer2 = [ones(m, 1) layer2];
z3 = layer2*Theta2';
layer3 = sigmoid(z3);
yMatrix = zeros(m, num_labels);
for i = 1 : m
yMatrix(i, y(i)) = 1;
end;
for i = 1 : m
J += sum(-1 * yMatrix(i,:).*log(layer3(i,:)) - (1-yMatrix(i,:)).*log(1-layer3(i,:)));
end;
J = J / m;
J += lambda/2/m * (sum(sum(Theta1(:, 2 : end).^ 2)) + sum(sum(Theta2(:, 2 : end).^ 2)));
2.1 sigmoidGradient.m
{ g ′ ( z ) = d d z g ( z ) = g ( z ) ( 1 − g ( z ) ) s i g m o i d ( z ) = g ( z ) = 1 1 + e − z \begin{cases} g'(z) = \frac{d}{dz}g(z) = g(z)(1-g(z)) & \\ sigmoid(z) = g(z) = \frac{1}{1+e^{-z}} & \end{cases} {g′(z)=dzdg(z)=g(z)(1−g(z))sigmoid(z)=g(z)=1+e−z1
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
2.2 randInitializeWeights.m
复粘…
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) * 2 * epsilon_init - epsilon_init;
% =========================================================================
end
2.3 nnCostFunction.m
补充反向传播算法
% Backpropagation
Delta1 = zeros(size(Theta1));
Delta2 = zeros(size(Theta2));
for t = 1 : m
delta3 = (layer3(t, :) - yMatrix(t, :))';
delta2 = (Theta2'*delta3)(2:end).*sigmoidGradient(z2(t, :))';
Delta2 += delta3*layer2(t, :);
Delta1 += delta2*layer1(t, :);
end;
Theta2_grad = Delta2 / m;
Theta1_grad = Delta1 / m;
2.5 nnCostFunction.m
补充正则化梯度
% regularized neural networks
Theta2_grad(:, 2:end) += lambda/m * Theta2(:, 2:end);
Theta1_grad(:, 2:end) += lambda/m * Theta1(:, 2:end);
// TODO: 待补充更多细节