作业下载 地址: https://download.csdn.net/download/wwangfabei1989/10301802
1. sigmoid梯度计算
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. 随机初始化权重
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
3.神经网络代价函数
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.
%
%--首先计算出 第三层的输出
X=[ones(m,1) X]
%第二层神经网络输出
secondlayer=sigmoid(X*Theta1');
%第三层 神经网络输出
O3=sigmoid([ones(m,1) secondlayer]*Theta2');
yk = zeros(num_labels, m); %初始化 所有 训练集 的 正确结果为0
for i=1:m,
yk(y(i),i)=1;%对 每一组 sample设置 其 实际值 为 1,其他 为 0.
end
J = (1/m)*sum(sum((-yk').*log(O3)-(1-yk').*log(1-O3)));
J=J+(lambda/(2*m))*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));
%按照 题目的步骤来写 就行了
for t=1:m,
% 正向传播 计算各节点值
a1 = X(t,:); %由于上面已经增加了 截距,故而在此处直接使用
z2 = Theta1 * a1';
a2 = sigmoid(z2);
a2 = [1 ; a2]; % 增加截距
z3 = Theta2 * a2;
a3 = sigmoid(z3); % 输出
% 反向传播
z2=[1; z2]; % 增加截距
delta_3 = a3 - yk(:,t); % 偏差值
delta_2 = (Theta2' * delta_3) .* sigmoidGradient(z2);
% 去除截距 节点
delta_2 = delta_2(2:end);
Theta2_grad = Theta2_grad + delta_3 * a2';
Theta1_grad = Theta1_grad + delta_2 * a1; % 此处 注意了 a1的size是1*401,而delta_2的size是25*1,故而此处不需要进行转置
end;
%Theta1_grad = Theta1_grad ./ m; 非正则化
%Theta2_grad = Theta2_grad ./ m;
Theta1_grad(:, 1) = Theta1_grad(:, 1) ./ m;%第1列 不进行 正则化
Theta1_grad(:, 2:end) = Theta1_grad(:, 2:end) ./ m + ((lambda/m) * Theta1(:, 2:end));
Theta2_grad(:, 1) = Theta2_grad(:, 1) ./ m;
Theta2_grad(:, 2:end) = Theta2_grad(:, 2:end) ./ m + ((lambda/m) * Theta2(:, 2:end));
% -------------------------------------------------------------
% =========================================================================
% Unroll gradients
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end
知乎: https://zhuanlan.zhihu.com/albertwang
微信公众号:AI-Research-Studio
下面是赞赏码