Coursera Machine Learning 第五周 quiz Programming Exercise 4: Neural Networks Learning
来源:互联网 发布:淘宝食品店铺运营技巧 编辑:程序博客网 时间:2024/06/11 18:49
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.% %计算J值X = [ones(m,1) X];for i = 1:m, %m为训练样本数,利用for遍历 z2 = Theta1 * X(i,:)'; %对第i个训练样本正向传播得到输出h(x),即为a3 a2 = sigmoid(z2); a2 = [1; a2]; z3 = Theta2 * a2; a3 = sigmoid(z3); J = J + sum(log(1 - a3)) + log(a3(y(i,:))) - log(1 - a3(y(i,:))); %由于输出为10维向量,而y的值是1-10的数字,所以可以用y的值指示a3那些元素加,哪些不加end %a3(y(i,:))及指示训练样本对应的a3的元素J = -1/m * J;temp = 0;for i = 1:hidden_layer_size, %对Theta1除了第一列(与偏置神经元对应的那列)元素的平方求和 for j = 2:(input_layer_size + 1), temp = temp + Theta1(i,j)^2; endendfor i = 1:num_labels, %对Theta2除了第一列(与偏置神经元对应的那列)元素的平方求和 for j = 2:(hidden_layer_size + 1), temp = temp + Theta2(i,j)^2; endendJ = J + lambda/(2*m)*temp;%利用反向传播法求取偏导数值,实际上这个循环可以和计算J值得循环合为一个,为了代码清晰,所以分开写了delta3 = zeros(num_labels,1); %反向传播,输出层的误差delta2 = zeros(size(Theta1)); %反向传播,隐藏层的误差;输入层不计算误差for i = 1:m, %m为训练样本数,利用for遍历 a1 = X(i,:)'; z2 = Theta1 * a1; %对第i个训练样本正向传播得到输出h(x),即为a3 a2 = sigmoid(z2); a2 = [1; a2]; z3 = Theta2 * a2; a3 = sigmoid(z3); delta3 = a3; %反向传播,计算得偏导数 delta3(y(i,:)) = delta3(y(i,:)) - 1; delta2 = Theta2' * delta3 .*[1;sigmoidGradient(z2)]; delta2 = delta2(2:end); Theta2_grad = Theta2_grad + delta3 * a2'; Theta1_grad = Theta1_grad + delta2 * a1';end Theta2_grad = 1/m * Theta2_grad + lambda/m * Theta2; %正则化,修正梯度值Theta2_grad(:,1) = Theta2_grad(:,1) - lambda/m * Theta2(:,1); %由于不惩罚偏执单元对应的列,所以把他减掉Theta1_grad = 1/m * Theta1_grad + lambda/m * Theta1; %同理修改Theta1_gradTheta1_grad(:,1) = Theta1_grad(:,1) - lambda/m * Theta1(:,1);% -------------------------------------------------------------% =========================================================================% Unroll gradientsgrad = [Theta1_grad(:) ; Theta2_grad(:)];endsigmoidGradient.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
1 0
- Coursera Machine Learning 第五周 quiz Programming Exercise 4: Neural Networks Learning
- Coursera Machine Learning 第五周 quiz Neural Networks: Learning
- Coursera Machine Learning 第五周 quiz Neural Networks: Learning
- coursera Machine Learning 第五周 测验quiz答案解析 Neural Networks: Learning
- Programming Exercise 4: Neural Networks Learning Machine Learning
- Coursera Machine Learning 第四周 quiz Programming Exercise 3 Multi-class Classification and Neural
- Coursera Machine Learning 第四周 quiz Neural Networks: Representation
- Coursera Machine Learning Week 4 - Neural Networks
- Coursera Machine Learning 第二周 quiz Programming Exercise 1: Linear Regression
- Coursera Machine Learning 第三周 quiz Programming Exercise 2: Logistic Regression
- Coursera Machine Learning 第七周 quiz Programming Exercise 6: Support Vector Machines
- Coursera Machine Learning 第八周 quiz Programming Exercise 7 K-means Clustering and Principal Component
- Machine Learning week 4 quiz: programming assignment-Multi-class Classification and Neural Networks
- Machine Learning week 4 quiz: Neural Networks: Representation
- coursera Machine Learning 第四周 测验quiz答案解析 Neural Networks: Representation
- Machine Learning week 5 quiz: Neural Networks: Learning
- Coursera Machine Learning 第三周 quiz Regularization
- Coursera Machine Learning 第六周 quiz Machine Learning System Design
- Type interface dxm.com.mapper.UserMapperI is already known to the MapperRegistry.
- Xcode 8.0无法注释的问题
- CODEVS 1380没有上司的舞会
- 【CUDA学习笔记】3.纹理引用API
- Redis-(Command.java)命令类
- Coursera Machine Learning 第五周 quiz Programming Exercise 4: Neural Networks Learning
- There are no resources that can be added or removed from the server...解决办法
- python学习笔记 进程和线程
- codevs1384黑色星期五【USACO】
- 实战c++中的vector系列--正确释放vector的内存(clear(), swap(), shrink_to_fit())
- linux下获得本地真实IP地址,非127.0.0.1
- CentOS 7 安装Mariadb 及详解
- hdu 3564 Another LIS(线段树+lis)
- JS与OC互相调用的一百种方法(包括WKWebView和UIWebView)