知识卡片
惰性学习把部分成本移到查询时
KNN等方法训练时主要保存和组织数据,预测时再查邻居;树或网络则通常先拟合压缩模型。实际训练和查询成本依实现、规模与索引而变,不能把“惰性”解释为始终无需训练代价。
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
- · 机器学习基础
原书出处 · 1 处
- · 查看原书依据
The lazy learner simply stores the training data and waits until testing data appears. Classification is done based on the most related data stored in training data. The K-NN algorithm is considered a lazy learner.
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第02章《机器学习基础》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/13_chapter02.xhtml)
- 结论依据:摘录中关于惰性学习把部分成本移到查询时的定义、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 lazy learner simply stores the training data and waits until testing data appears. Classification is done based on the most related data stored in training data. The K-NN algorithm is considered a lazy learner.