知识卡片
零频会阻断概率组合
用频率估计类别下的特征概率时,某种特征值没有出现,估计可能为零;多个条件概率相乘时,一个零就能把该类别的得分压成零。未观察到不等于现实中不可能,解释预测时要检查这种估计边界。
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
feature classes. This algorithm works best if the variables are discrete and not continuous. The main disadvantage of naive Bayes is the assumption that features are independent of each other, which is not possible in real life. Moreover, if there is no training set for a particular class feature, this may result in a posterior probability of zero. This is known as the zero-frequency problem.
参考来源
- 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第01章《推荐系统的机器学习方法》(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-C1.html)
- 结论依据:摘录中关于零频会阻断概率组合的定义、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:feature classes. This algorithm works best if the variables are discrete and not continuous. The main disadvantage of naive Bayes is the assumption that features are independent of each other, which is not possible in real life. Moreover, if there is no training set for a particular class feature, this may result in a posterior probability of zero. This is known as the zero-frequency problem.