模型选择与评价.pptxVIP

Model Selection and Evaluation ;What is Model Selection?;What are potential issues with Model Selection?;Performance Assessment: Loss Function;Training Error;Generalization error or test error: -- the expected prediction error over an independent test sample. (真风险，推广性误差) For quantitative response Y: For categorical response G: ;Bias(偏置), Variance(估计方差) and Model Complexity;What do we see from the preceding figure?;Goals;Splitting the data;Bias-variance Decomposition(1);Bias-Variance Decomposition(2);监督式机器学习--错误率的点估计;;;;;监督式机器学习--有限样本下错误率的区间估计;;例：Comparison between Support Vector