自我学习

今天让我们来完成自我学习的代码。完成这个代码需要结合稀疏自编码和softmax分类器，具体的可以看我以前的博客。

依赖

MNIST Dataset
Support functions for loading MNIST in Matlab
Starter Code (stl_exercise.zip)

第一步:生成相应的输入和测试数据集

这需要有MNIST的数据，这部分代码已经在文件里面自带。

第二步:训练相应的自编码器

我们将使用无标签数据(从5到9)来训练一个稀疏自编码，使用sparseAutoencoderCost.m，来完成相应的操作。这个在前面的博客里面的我已经完成了。完成这一步，我的电脑差不多跑了将近40分钟。

我们仅需要对stlExercise.m里面加入相应的代码(Step 2里面)

%% ----------------- YOUR CODE HERE ----------------------
%  Find opttheta by running the sparse autoencoder on
%  unlabeledTrainingImagesopttheta = theta; options.Method = 'lbfgs'; % Here, we use L-BFGS to optimize our cost% function. Generally, for minFunc to work, you% need a function pointer with two outputs: the% function value and the gradient. In our problem,% sparseAutoencoderCost.m satisfies this.
options.MaxIter = 400;	  % Maximum number of iterations of L-BFGS to run 
options.Display = 'iter';
options.GradObj = 'on';[opttheta, cost] = fminlbfgs( @(p) sparseAutoencoderCost(p, ...inputSize, hiddenSize, ...lambda, sparsityParam, ...beta, unlabeledData), ...theta, options);% save('min_func_result.mat', 'trainSet', 'testSet', 'unlabeledData', 'trainData', 'trainLabels', 'testData', 'testLabels', 'opttheta');% load('min_func_result.mat');

最终会得到下面的结果

第3步:导出特征

在稀疏自编码后，我们将导出特征。我们得完成feedForwardAutoEncoder.m里面的代码。

这步我们得自己来写。

function [activation] = feedForwardAutoencoder(theta, hiddenSize, visibleSize, data)% theta: trained weights from the autoencoder
% visibleSize: the number of input units (probably 64) 
% hiddenSize: the number of hidden units (probably 25) 
% data: Our matrix containing the training data as columns.  So, data(:,i) is the i-th training example. % We first convert theta to the (W1, W2, b1, b2) matrix/vector format, so that this 
% follows the notation convention of the lecture notes. W1 = reshape(theta(1:hiddenSize*visibleSize), hiddenSize, visibleSize);
b1 = theta(2*hiddenSize*visibleSize+1:2*hiddenSize*visibleSize+hiddenSize);%% ---------- YOUR CODE HERE --------------------------------------
%  Instructions: Compute the activation of the hidden layer for the Sparse Autoencoder.
m=size(data,2);
z_2=W1*data+repmat(b1,1,m);
a_2=sigmoid(z_2);
activation=a_2;%-------------------------------------------------------------------end%-------------------------------------------------------------------
% Here's an implementation of the sigmoid function, which you may find useful
% in your computation of the costs and the gradients.  This inputs a (row or
% column) vector (say (z1, z2, z3)) and returns (f(z1), f(z2), f(z3)). function sigm = sigmoid(x)sigm = 1 ./ (1 + exp(-x));
end

第4步:我们需要训练和测试逻辑回归模型

我们得通过先前写的代码softmaxTrain.m来完成相应的功能。

我们在stlExercise.m文件里面的第4步改成相应的

%% ----------------- YOUR CODE HERE ----------------------
%  Use softmaxTrain.m from the previous exercise to train a multi-class
%  classifier. %  Use lambda = 1e-4 for the weight regularization for softmax% You need to compute softmaxModel using softmaxTrain on trainFeatures and
% trainLabelslambda = 1e-4;
numClasses = numel(unique(trainLabels));softmaxModel = softmaxTrain(hiddenSize, numClasses, lambda, ...trainFeatures, trainLabels, options);

第5步:完成对测试集的分类

我们可以运行程序，看看输出的结果。