知识卡片
测试集应与训练用途隔离
测试可从原始数据中划出,但不应又属于实际拟合参数的训练子集。评价能否代表部署,还取决于时间、群组、重复记录和目标分布;训练测试都高分也不能排除所有泄漏或漂移。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
The test data set is a subset of the training data set that is utilized to give an objective evaluation of a final model. It is a set of examples used to assess the performance or generalization of a fully specified classifier.[8][9] A test data set is independent of the training data. It should follow the same probability distribution as the training data set. If
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第03章《机器学习流程与数据管理》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/14_chapter03.xhtml)
- 结论依据:摘录中关于测试集应与训练用途隔离的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:The test data set is a subset of the training data set that is utilized to give an objective evaluation of a final model. It is a set of examples used to assess the performance or generalization of a fully specified classifier.[8][9] A test data set is independent of the training data. It should follow the same probability distribution as the training data set. If