知识卡片
降维工具要与下游目标一致
PCA强调线性方差方向,LSA常用于未中心化文本矩阵,t-SNE主要用于可视化局部邻域。它们不保证最大化所有成对差异,也不应把t-SNE坐标默认当可靠回归特征;先明确保留什么再比较任务收益。
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
Use scatter plots and scatter matrices on low-dimensional features and targets to make sure you aren’t missing some obvious patterns. Plot high-dimensional data as a raw image to discover shifting across features.5 Try PCA on high-dimensional data (LSA on NLP data) when you want to maximize the differences between pairs of vectors. Use nonlinear dimension reduction, like t-SNE, when you want to find matches between
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》附录D《附录D:机器学习工具与技术》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/appendix-d.html)
- 结论依据:摘录中关于降维工具要与下游目标一致的定义、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:Use scatter plots and scatter matrices on low-dimensional features and targets to make sure you aren’t missing some obvious patterns. Plot high-dimensional data as a raw image to discover shifting across features.5 Try PCA on high-dimensional data (LSA on NLP data) when you want to maximize the differences between pairs of vectors. Use nonlinear dimension reduction, like t-SNE, when you want to find matches between