知识卡片
规则维护与样本学习有别
规则过滤由人或规则系统明确指定匹配条件,垃圾内容变化后往往需要更新。监督学习从已标注样本估计分类边界,减少逐条手写规则的依赖,但仍需要有代表性的数据、评估和维护,并非永远自动适应。
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
The major drawback of the rule-based approach is that these rules must be updated frequently in a dynamic context. Machine learning is a practical and viable alternative approach since no specific rules are generated explicitly; instead, a set of training samples is utilized [11-13]. Machine learning algorithms develop multiple models using different data sets collected from some standard repository or corpus, and each model is
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:摘录中关于规则维护与样本学习有别的定义、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 major drawback of the rule-based approach is that these rules must be updated frequently in a dynamic context. Machine learning is a practical and viable alternative approach since no specific rules are generated explicitly; instead, a set of training samples is utilized [11-13]. Machine learning algorithms develop multiple models using different data sets collected from some standard repository or corpus, and each model is