【DeepLearning】Exercise:Learning color features with Sparse Autoencoders
Exercise:Learning color features with Sparse Autoencoders
习题链接:Exercise:Learning color features with Sparse Autoencoders
sparseAutoencoderLinearCost.m
function [cost,grad,features] = sparseAutoencoderLinearCost(theta, visibleSize, hiddenSize, ...
lambda, sparsityParam, beta, data)
% -------------------- YOUR CODE HERE --------------------
% Instructions:
% Copy sparseAutoencoderCost in sparseAutoencoderCost.m from your
% earlier exercise onto this file, renaming the function to
% sparseAutoencoderLinearCost, and changing the autoencoder to use a
% linear decoder.
% -------------------- YOUR CODE HERE -------------------- % W1 is a hiddenSize * visibleSize matrix
W1 = reshape(theta(:hiddenSize*visibleSize), hiddenSize, visibleSize);
% W2 is a visibleSize * hiddenSize matrix
W2 = reshape(theta(hiddenSize*visibleSize+:*hiddenSize*visibleSize), visibleSize, hiddenSize);
% b1 is a hiddenSize * vector
b1 = theta(*hiddenSize*visibleSize+:*hiddenSize*visibleSize+hiddenSize);
% b2 is a visible * vector
b2 = theta(*hiddenSize*visibleSize+hiddenSize+:end); numCases = size(data, ); % forward propagation
z2 = W1 * data + repmat(b1, , numCases);
a2 = sigmoid(z2);
z3 = W2 * a2 + repmat(b2, , numCases);
a3 = z3; % error
sqrerror = (data - a3) .* (data - a3);
error = sum(sum(sqrerror)) / ( * numCases);
% weight decay
wtdecay = (sum(sum(W1 .* W1)) + sum(sum(W2 .* W2))) / ;
% sparsity
rho = sum(a2, ) ./ numCases;
divergence = sparsityParam .* log(sparsityParam ./ rho) + ( - sparsityParam) .* log(( - sparsityParam) ./ ( - rho));
sparsity = sum(divergence); cost = error + lambda * wtdecay + beta * sparsity; % delta3 is a visibleSize * numCases matrix
delta3 = -(data - a3);
% delta2 is a hiddenSize * numCases matrix
sparsityterm = beta * (-sparsityParam ./ rho + (-sparsityParam) ./ (-rho));
delta2 = (W2' * delta3 + repmat(sparsityterm, 1, numCases)) .* sigmoiddiff(z2); W1grad = delta2 * data' ./ numCases + lambda * W1;
b1grad = sum(delta2, ) ./ numCases; W2grad = delta3 * a2' ./ numCases + lambda * W2;
b2grad = sum(delta3, ) ./ numCases; %-------------------------------------------------------------------
% After computing the cost and gradient, we will convert the gradients back
% to a vector format (suitable for minFunc). Specifically, we will unroll
% your gradient matrices into a vector. grad = [W1grad(:) ; W2grad(:) ; b1grad(:) ; b2grad(:)]; end function sigm = sigmoid(x) sigm = ./ ( + exp(-x));
end function sigmdiff = sigmoiddiff(x) sigmdiff = sigmoid(x) .* ( - sigmoid(x));
end
如果跑出来是这样的,可能是把a3 = z3写成了a3 = sigmoid(z3)
【DeepLearning】Exercise:Learning color features with Sparse Autoencoders的更多相关文章
- 【DeepLearning】Exercise:Self-Taught Learning
Exercise:Self-Taught Learning 习题链接:Exercise:Self-Taught Learning feedForwardAutoencoder.m function [ ...
- 【DeepLearning】Exercise:Convolution and Pooling
Exercise:Convolution and Pooling 习题链接:Exercise:Convolution and Pooling cnnExercise.m %% CS294A/CS294 ...
- 【DeepLearning】Exercise: Implement deep networks for digit classification
Exercise: Implement deep networks for digit classification 习题链接:Exercise: Implement deep networks fo ...
- 【DeepLearning】Exercise:PCA and Whitening
Exercise:PCA and Whitening 习题链接:Exercise:PCA and Whitening pca_gen.m %%============================= ...
- 【DeepLearning】Exercise:Softmax Regression
Exercise:Softmax Regression 习题的链接:Exercise:Softmax Regression softmaxCost.m function [cost, grad] = ...
- 【DeepLearning】Exercise:PCA in 2D
Exercise:PCA in 2D 习题的链接:Exercise:PCA in 2D pca_2d.m close all %%=================================== ...
- 【DeepLearning】Exercise:Vectorization
Exercise:Vectorization 习题的链接:Exercise:Vectorization 注意点: MNIST图片的像素点已经经过归一化. 如果再使用Exercise:Sparse Au ...
- 【DeepLearning】Exercise:Sparse Autoencoder
Exercise:Sparse Autoencoder 习题的链接:Exercise:Sparse Autoencoder 注意点: 1.训练样本像素值需要归一化. 因为输出层的激活函数是logist ...
- 【UFLDL】Exercise: Convolutional Neural Network
这个exercise需要完成cnn中的forward pass,cost,error和gradient的计算.需要弄清楚每一层的以上四个步骤的原理,并且要充分利用matlab的矩阵运算.大概把过程总结 ...
随机推荐
- You must have a copy of the scp binary locally to use the scp feature
在运行docker-machine scp 命令的时候,报错: "You must have a copy of the scp binary locally to use the scp ...
- 看见上帝的 10 个公式……
原文 Top Ten Greatest Equations Ever 本文内容 No.1 麦克斯韦方程组 No.2 欧拉方程 No.3 牛顿第二定律 No.4 毕达哥拉斯定理 No.5 薛定谔方程 N ...
- linux install nodejs
下载/安装python yum install -y bzip2* #nodejs 0.8.5需要,请安装python前,先安装此模块. wget http://www.python.org/ft ...
- C#.NET常见问题(FAQ)-如何让listView如何选中一行
把FullRowSelect设置为True 更多教学视频和资料下载,欢迎关注以下信息: 我的优酷空间: http://i.youku.com/acetaohai123 我的在线论坛: ht ...
- Discuz常见小问题-如何安装模板,使用模板
点击应用,获取更多插件 在模板页面中选择需要的类型(需要注册一个账号) 找好一个模板之后,点击安装应用(一般也会有演示) 安装完成之后可以在界面-风格管理中选择安装好的模板,选中新的模板,点击提交即可 ...
- 【转】java并发编程系列之ReadWriteLock读写锁的使用
前面我们讲解了Lock的使用,下面我们来讲解一下ReadWriteLock锁的使用,顾明思义,读写锁在读的时候,上读锁,在写的时候,上写锁,这样就很巧妙的解决synchronized的一个性能问题:读 ...
- 微信小程序 - 弹出层组件
需要的可以下载示例:maskalert
- Android下雪动画的实现
原文链接 : Snowfall 原文作者 : Styling Android 译文出自 : hanks.xyz 译者 : hanks-zyh 校对者: desmond1121 状态 : 完毕 这本是一 ...
- 算法笔记_233:二阶魔方旋转(Java)
目录 1 问题描述 2 解决方案 1 问题描述 魔方可以对它的6个面自由旋转. 我们来操作一个2阶魔方(如图1所示): 为了描述方便,我们为它建立了坐标系. 各个面的初始状态如下:x轴正向:绿x轴 ...
- Mule 入门之:环境搭建
Mule 入门之:环境搭建 JDK1.5或以上版本Eclipse3.3以上 下载与安装:目前最新版本为2.2.1 下载,下载后得到一名为mule-standalone-2.2.1.zip的压缩文件,解 ...