【DeepLearning】Exercise:Self-Taught Learning

Exercise:Self-Taught Learning

习题链接：Exercise:Self-Taught Learning

feedForwardAutoencoder.m

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.
activation = sigmoid(W1 * data + repmat(b1, 1, size(data, 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

stlExercise.m

%% CS294A/CS294W Self-taught Learning Exercise

%  Instructions
%  ------------
%
%  This file contains code that helps you get started on the
%  self-taught learning. You will need to complete code in feedForwardAutoencoder.m
%  You will also need to have implemented sparseAutoencoderCost.m and
%  softmaxCost.m from previous exercises.
%
%% ======================================================================
%  STEP : Here we provide the relevant parameters values that will
%  allow your sparse autoencoder to get good filters; you do not need to
%  change the parameters below.

inputSize  =  * ;
numLabels  = ;
hiddenSize = ;
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-;       % weight decay parameter
beta = ;            % weight of sparsity penalty term
maxIter = ;

%% ======================================================================
%  STEP : Load data from the MNIST database
%
%  This loads our training and test data from the MNIST database files.
%  We have sorted the data for you in this so that you will not have to
%  change it.

% Load MNIST database files
mnistData   = loadMNISTImages('mnist/train-images-idx3-ubyte');
mnistLabels = loadMNISTLabels('mnist/train-labels-idx1-ubyte');

% Set Unlabeled Set (All Images)

% Simulate a Labeled and Unlabeled set
labeledSet   = find(mnistLabels >=  & mnistLabels <= );
unlabeledSet = find(mnistLabels >= );

numTrain = round(numel(labeledSet)/);
trainSet = labeledSet(:numTrain);
testSet  = labeledSet(numTrain+:end);

unlabeledData = mnistData(:, unlabeledSet);

trainData   = mnistData(:, trainSet);
trainLabels = mnistLabels(trainSet)' + 1; % Shift Labels to the Range 1-5

testData   = mnistData(:, testSet);
testLabels = mnistLabels(testSet)' + 1;   % Shift Labels to the Range 1-5

% Output Some Statistics
fprintf('# examples in unlabeled set: %d\n', size(unlabeledData, ));
fprintf('# examples in supervised training set: %d\n\n', size(trainData, ));
fprintf('# examples in supervised testing set: %d\n\n', size(testData, ));

%% ======================================================================
%  STEP : Train the sparse autoencoder
%  This trains the sparse autoencoder on the unlabeled training
%  images. 

%  Randomly initialize the parameters
theta = initializeParameters(hiddenSize, inputSize);

%% ----------------- YOUR CODE HERE ----------------------
%  Find opttheta by running the sparse autoencoder on
%  unlabeledTrainingImages

%  Use minFunc to minimize the function
addpath minFunc/
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 = maxIter;% Maximum number of iterations of L-BFGS to run
options.display = 'on';

[opttheta, cost] = minFunc( @(p) sparseAutoencoderCost(p, ...
                                   inputSize, hiddenSize, ...
                                   lambda, sparsityParam, ...
                                   beta, unlabeledData), ...
                              theta, options);

%% -----------------------------------------------------

% Visualize weights
W1 = reshape(opttheta(:hiddenSize * inputSize), hiddenSize, inputSize);
display_network(W1');

%%======================================================================
%% STEP : Extract Features from the Supervised Dataset
%
%  You need to complete the code in feedForwardAutoencoder.m so that the
%  following command will extract features from the data.

trainFeatures = feedForwardAutoencoder(opttheta, hiddenSize, inputSize, ...
                                       trainData);

testFeatures = feedForwardAutoencoder(opttheta, hiddenSize, inputSize, ...
                                       testData);

%%======================================================================
%% STEP : Train the softmax classifier

%% ----------------- YOUR CODE HERE ----------------------
%  Use softmaxTrain.m from the previous exercise to train a multi-class
%  classifier. 

%  Use lambda = 1e- for the weight regularization for softmax

% You need to compute softmaxModel using softmaxTrain on trainFeatures and
% trainLabels

lambda = 1e-;
options.maxIter = maxIter;
[softmaxModel] = softmaxTrain(hiddenSize, numLabels, lambda, trainFeatures, trainLabels, options);

%% -----------------------------------------------------

%%======================================================================
%% STEP : Testing 

%% ----------------- YOUR CODE HERE ----------------------
% Compute Predictions on the test set (testFeatures) using softmaxPredict
% and softmaxModel
[pred] = softmaxPredict(softmaxModel, testFeatures);

%% -----------------------------------------------------

% Classification Score
fprintf('Test Accuracy: %f%%\n', *mean(pred(:) == testLabels(:)));

% (note that we shift the labels by , so that digit  now corresponds to
%  label )
%
% Accuracy is the proportion of correctly classified images
% The results for our implementation was:
%
% Accuracy: 98.3%
%
% 

Test Accuracy: 98.208916%