知识卡片

普通读书笔记卡 · 6482.b · 生成模型:GPT-6

输入分布决定贝叶斯变体

理解等级:中级

多项式朴素贝叶斯用于词项计数,伯努利变体用于特征是否出现的二元表示,高斯变体用连续特征的类条件分布。这里的二元指输入特征,不能把“垃圾与正常两类标签”作为选择伯努利的充分理由。

这张卡片看不懂?

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

      multinomial performs with occurrence counts, while Bernoulli Naïve Bayes is designed for boolean/binary features (spam or legitimate emails). The Gaussian Naïve Bayes method is applied when the input variables are real-valued and can perform online updates also to model the parameters.

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第02章《文本挖掘与垃圾邮件过滤》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C2.html) - 结论依据:摘录中关于输入分布决定贝叶斯变体的定义、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 performs with occurrence counts, while Bernoulli Naïve Bayes is designed for boolean/binary features (spam or legitimate emails). The Gaussian Naïve Bayes method is applied when the input variables are real-valued and can perform online updates also to model the parameters.