知识卡片
袋外行是重抽未选中的样本
一次抽n次的bootstrap中,部分原始训练行一次也未出现,可用于该树的袋外评价,比例大样本下约e⁻¹。它不是先从已抽中的样本再划出三分之一;每棵树的袋外集合可以不同。
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
- · 监督学习模型
原书出处 · 1 处
- · 查看原书依据
As mentioned earlier, the random forest algorithm is made up of a collection of decision trees. Each tree in the ensemble consists of a data sample drawn from a training set with a replacement known as a bootstrap sample. Out of that training sample one-third of it is set aside as test data. Depending on the type of problem—classification or regression the result of the
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第06章《监督学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/19_chapter06.xhtml)
- 结论依据:摘录中关于袋外行是重抽未选中的样本的定义、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:As mentioned earlier, the random forest algorithm is made up of a collection of decision trees. Each tree in the ensemble consists of a data sample drawn from a training set with a replacement known as a bootstrap sample. Out of that training sample one-third of it is set aside as test data. Depending on the type of problem—classification or regression the result of the