Coursera—machine learning(Andrew Ng)第五周编程作业
来源:互联网 发布:手机裁剪图片软件 编辑:程序博客网 时间:2024/05/18 10:13
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)) %g'(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 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
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 networkTheta1 = 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 variablesm = 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.%% part 1 % Theta1 has size 25 x 401 % Theta2 has size 10 x 26 h = eye(num_labels);y = h(y,:); %5000x10 这两条语句的意义在将y中的值变为0-1表示a1 = [ones(m, 1) X]; %5000x401 z2 = a1 * Theta1' ; a2 = sigmoid(z2); n = size(a2,1); a2 = [ones(n, 1) a2] ; %5000x26 a3 = sigmoid(a2 * Theta2'); %5000x10 J = sum( sum( -y.* log(a3) - (1-y).*log(1-a3) ))/ m; % pay attention :" Theta1(:,2:end) " , no "Theta1" . regularized = lambda/(2*m) * (sum(sum(Theta1(:,2:end).^2)) + sum(sum(Theta2(:,2:end).^2)) ); J = J + regularized; %part2delta3 = a3 - y; %5000*10delta2 = delta3 * Theta2; %5000*26delta2 = delta2(:, 2 : end);delta2 = delta2 .* sigmoidGradient(z2); %5000*25Delta_1 = zeros(size(Theta1));Delta_2 = zeros(size(Theta2));Delta_1 = Delta_1 + delta2' * a1;Delta_2 = Delta_2 + delta3' * a2;Theta1_grad = ((1 / m) * Delta_1) + ((lambda / m) * Theta1); Theta2_grad = ((1 / m) * Delta_2) + ((lambda / m) * Theta2);Theta1_grad(:, 1) = Theta1_grad(:, 1) - ((lambda / m) * (Theta1(:, 1)));Theta2_grad(:, 1) = Theta2_grad(:, 1) - ((lambda / m) * (Theta2(:, 1))); %这两行语句代表...%Theta1_grad, Theta2_grad中第一列theta值不需要正则化% -------------------------------------------------------------% =========================================================================% Unroll gradientsgrad = [Theta1_grad(:) ; Theta2_grad(:)];end
坚持。
By 信念
阅读全文
0 0
- Coursera—machine learning(Andrew Ng)第五周编程作业
- Coursera—machine learning(Andrew Ng)第二周编程作业
- Coursera—machine learning(Andrew Ng)第三周编程作业
- Coursera—machine learning(Andrew Ng)第六周编程作业
- Coursera—machine learning(Andrew Ng)第七周编程作业
- Coursera—machine learning(Andrew Ng)第八周编程作业
- Coursera—machine learning(Andrew Ng)第四周编程作业
- coursera Machine Learning, Andrew Ng
- Andrew Ng -machine learning 课堂笔记(二)第五周
- andrew ng的machine learning第一次作业
- Andrew Coursera Machine Learning
- Andrew Ng's Machine Learning in Coursera(I)
- coursera Machine learning Andrew NG 笔记(一)
- Machine Learning - Andrew Ng on Coursera (Week 1)
- Machine Learning - Andrew Ng on Coursera (Week 2)
- Machine Learning - Andrew Ng on Coursera (Week 3)
- Machine Learning - Andrew Ng on Coursera (Week 4)
- Machine Learning - Andrew Ng on Coursera (Week 5)
- 如何了解国家级期刊发表流程
- linux select函数详解
- 关于@ResponseBody 注解 无法将返回数据转化为json
- CSS3选择器
- HttpFileCollection 实现多文件上传
- Coursera—machine learning(Andrew Ng)第五周编程作业
- FCN全卷积网原理
- npm加速
- 计算1+2+3+4+5+.....+n (用三大循环)
- Eclipse搭建maven项目—简单测试程序(3)
- ubuntu64位(x86)下科大讯飞sdk使用注意事项
- unblock with 'mysqladmin flush-hosts'Connection closed by foreign host.
- 绑定服务&绑定远程服务
- P1421 小玉买文具