UFLDL Exercise:Softmax Regression

练习题网址：http://deeplearning.stanford.edu/wiki/index.php/Exercise:Softmax_Regression

softmaxCost.m

function [cost, grad] = softmaxCost(theta, numClasses, inputSize, lambda, data, labels)

% numClasses - the number of classes 
% inputSize - the size N of the input vector
% lambda - weight decay parameter
% data - the N x M input matrix, where each column data(:, i) corresponds to
%        a single test set
% labels - an M x 1 matrix containing the labels corresponding for the input data
%

% Unroll the parameters from theta
theta = reshape(theta, numClasses, inputSize);

numCases = size(data, 2);

groundTruth = full(sparse(labels, 1:numCases, 1));
cost = 0;

thetagrad = zeros(numClasses, inputSize);

%% ---------- YOUR CODE HERE --------------------------------------
%  Instructions: Compute the cost and gradient for softmax regression.
%                You need to compute thetagrad and cost.
%                The groundTruth matrix might come in handy.

M = theta * data;
M = bsxfun(@minus,M,max(M,[],1));
Exp_M = exp(M);
p = bsxfun(@rdivide,Exp_M,sum(Exp_M));
% general cost
% cost = cost - 1/numCases*sum(sum(groundTruth.*log(p)));
cost = cost - 1/numCases * groundTruth(:)' * log(p(:));

% add Weight Decay
cost = cost + lambda/2 * sum(theta(:).^2);

% compute thetagrad
thetagrad = -1/numCases*(groundTruth - p)*data'+lambda*theta;

% M = bsxfun(@minus,theta*data,max(theta*data, [], 1));
% M = exp(M);
% p = bsxfun(@rdivide, M, sum(M));
% cost = -1/numCases * groundTruth(:)' * log(p(:)) + lambda/2 * sum(theta(:) .^ 2);
% thetagrad = -1/numCases * (groundTruth - p) * data' + lambda * theta;

% ------------------------------------------------------------------
% Unroll the gradient matrices into a vector for minFunc
grad = [thetagrad(:)];
end

softmaxPredict.m

function [pred] = softmaxPredict(softmaxModel, data)

% softmaxModel - model trained using softmaxTrain
% data - the N x M input matrix, where each column data(:, i) corresponds to
%        a single test set
%
% Your code should produce the prediction matrix 
% pred, where pred(i) is argmax_c P(y(c) | x(i)).
 
% Unroll the parameters from theta
theta = softmaxModel.optTheta;  % this provides a numClasses x inputSize matrix
pred = zeros(1, size(data, 2));

%% ---------- YOUR CODE HERE --------------------------------------
%  Instructions: Compute pred using theta assuming that the labels start 
%                from 1.
M = theta*data;
M = bsxfun(@minus,M,max(M));
Exp_M = exp(M);
p = bsxfun(@rdivide,Exp_M,sum(Exp_M));
[~,pred] = max(p);
% ---------------------------------------------------------------------

end