【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 Autoencoder中的sampleIMAGES.m进行归一化，

将使得训练得到的可视化权值如下图：

更改train.m的参数设置

visibleSize = 28*28;   % number of input units 
hiddenSize = 196;     % number of hidden units 
sparsityParam = 0.1;   % desired average activation of the hidden units.
                     % (This was denoted by the Greek alphabet rho, which looks like a lower-case "p",
             %  in the lecture notes). 
lambda = 3e-3;     % weight decay parameter       
beta = 3;            % weight of sparsity penalty term 

更改sampleIMAGES.m

function patches = sampleIMAGES()
% sampleIMAGES
% Returns 10000 patches for training

load images;    % load images from disk 

patchsize = 28;  % we'll use 28x28 patches 
numpatches = 10000;

% Initialize patches with zeros.  Your code will fill in this matrix--one
% column per patch, 10000 columns. 
patches = zeros(patchsize*patchsize, numpatches);

%% ---------- YOUR CODE HERE --------------------------------------
%  Instructions: Fill in the variable called "patches" using data 
%  from images.  

patches = images(:, 1:10000);

训练得到的W1可视化：