知识卡片
朴素贝叶斯变体匹配特征分布
Multinomial常建模词计数,Bernoulli建模是否出现,Gaussian用类内连续特征的高斯似然。选择时检查值域与条件分布假设,不把“连续”直接当所有类别共享同一个高斯。
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
Multinomial Naïve Bayes: one of the common applications of this classifier is in document classification problem, that is, whether a document belongs to the category of technology, finance, sports, politics, and so on. The features or the predictors used by this classifier are the frequency of words present in the document.
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:摘录中关于朴素贝叶斯变体匹配特征分布的定义、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:Multinomial Naïve Bayes: one of the common applications of this classifier is in document classification problem, that is, whether a document belongs to the category of technology, finance, sports, politics, and so on. The features or the predictors used by this classifier are the frequency of words present in the document.