机器学习
月暗云霄
这个作者很懒,什么都没留下…
展开
-
吴恩达机器学习作业8
estimateGaussianmu = sum(X) / m;sigma2 = sum((X - repmat(mu,m,1)) .^ 2) / m;selectThresholdpredictions = (pval < epsilon);tp = sum((predictions == 1) & (yval == 1));fp = sum((predictions == 1) & (yval == 0));fn = sum((predictions == 0)原创 2020-08-14 14:11:42 · 159 阅读 · 0 评论 -
吴恩达机器学习作业7
pcasigma = X' * X / m;[U,S,V] = svd(sigma);projectDataU_reduce = U(:,1:K);Z = X * U_reduce;recoverDataU_reduce = U(:,1:K);X_rec = Z * U_reduce';findClosestCentroidsm = size(X,1);for i = 1:m ind_k = zeros(K,1); for j = 1:K ind_k(j)原创 2020-08-12 13:28:54 · 288 阅读 · 0 评论 -
吴恩达机器学习作业6
gaussianKernelsim = exp(-sum((x1 - x2).^ 2) / (2 * (sigma^2)));dataset3Paramsparams = [0.01,0.03,0.1,0.3,1,3,10,30];MinError = 10000.0;for Cval = params, for sigVal = params, model = svmTrain(X,y,Cval,@(x1,x2) gaussianKernel(x1,x2,sigVal));原创 2020-08-10 17:02:51 · 240 阅读 · 0 评论 -
吴恩达机器学习作业5
linearRegCostFunctionh = X * theta;J = sum((h - y).^ 2) / (2 * m) + lambda / (2 * m) * sum(theta(2:end) .^ 2);grad = X' * (h - y) / m;grad(2:end) = grad(2:end) + lambda / m * theta(2:end);learningCurvefor i = 1:m [theta] = trainLinearReg(X(1:i,:原创 2020-08-09 15:21:44 · 257 阅读 · 0 评论 -
吴恩达机器学习作业4
sigmoidGradientvar foo = 'bar';randInitializeWeightsvar foo = 'bar';nnCostFunction// An highlighted blockvar foo = 'bar';原创 2020-08-08 22:03:45 · 235 阅读 · 0 评论 -
吴恩达机器学习作业3
lrCostFunctionh = sigmoid(X * theta);temp = theta;temp(1) = 0;grad = X' *(h - y) ./ m + lambda / m * temp;J = lambda / (2 * m) *(temp' * temp) + (y' * log(h) + (1 - y)' * log(1 - h)) / ( - m)oneVsAllfor c = 1:num_labels initial_theta = zeros(n原创 2020-08-07 20:20:26 · 645 阅读 · 0 评论 -
吴恩达机器学习作业2
plotDatapos = find(y == 1)neg = find(y == 0)% 属于分类1的样本赋值为pos,属于分类2的样本赋值为negplot(X(pos,1),X(pos,2),'k+','LineWidth',2,'MarkerSize',7)plot(X(neg,1),X(neg,2),'ko','MarkerFaceColor','y','MarkerSize',7)% X(pos, 1), X(pos, 2)表示分类1样本的横纵坐标,'k+'表示线性为加号型、黑色,L原创 2020-07-21 17:14:24 · 402 阅读 · 0 评论 -
吴恩达机器学习作业1
warmUp返回一个5阶单位矩阵A = eye(5)plotDataplot(x,y,'rx','MarkerSize',10)ylabel('Profit in $10,000s')xlabel('Population of City in 10,000s')computeCosth = x * thetaJ = 0for i = 1:m J = J +(h(i) - y(i)) * (h(i) - y(i)) endJ = J / (2 * m)g原创 2020-07-20 19:48:30 · 220 阅读 · 0 评论