Coursera-MachineLearning-Week4编程题目整理

lrCostFunction.m (logistic regression cost function)

J = 1./m*(-y'*log(sigmoid(X*theta))-(1-y')*log(1-sigmoid(X*theta)));  %计算代价函数J
J = J + lambda/(2*m)*(sum(theta.^2)-theta(1).^2);  %引入正则项，注意去掉常数项系数
grad = 1./m*X'*(sigmoid(X*theta)-y);  %计算梯度
grad = grad + lambda/m*theta;  %引入正则项
grad(1) = grad(1) - lambda/m*theta(1);  %去掉常数项

oneVsAll.m

initial_theta = zeros(n+1,1);
options = optimset('GradObj', 'on', 'MaxIter', 50);
for c = 1:num_labels
    [theta] = fmincg (@(t)(lrCostFunction(t, X, (y == c), lambda)),initial_theta, options);
    all_theta(c,:) = theta';
end

predictOneVsAll.m

[c,p] = max(sigmoid(X*all_theta'),[],2);  %每行取最大值，最大的就是对应标签

predict.m

X = [ones(m,1) X];  %追加常数项
a2 = sigmoid(X*Theta1');  %第一隐藏层的输出
a2 = [ones(size(a2,1),1) a2];
a3 = (sigmoid(a2*Theta2'));  %第二隐藏层的输出
[c, p] = max(a3, [], 2);  %选择每行中最大的值作为预测