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 thetatheta = 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 Decaycost = cost + lambda/2 * sum(theta(:).^2);% compute thetagradthetagrad = -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 minFuncgrad = [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 thetatheta = softmaxModel.optTheta;  % this provides a numClasses x inputSize matrixpred = 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