知识卡片

普通读书笔记卡 · 6488.j · 生成模型:GPT-6

冗余情境需检查信息关系

理解等级:高级

本章用信息增益选情境属性,并在同一维度内保留一个代表。例如已知星期几时,可以推出工作日或周末标签,两者可能重复。但每维只能选一个是该方法约束,不是一般规律;不同粒度也可能保留互补信息。

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

      target domain separately. In the CD-CARS, the information gain measure is considered, selecting only the contextual attribute with the highest information gain. Only one context can be chosen for each dimension. For instance, suppose the day was pointed out as the attribute with the highest information gain, followed by DayType. The algorithm selects only the Day attribute since it encapsulates the same information in DayType.

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第04章《多领域情境推荐的张量分解》(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-C4.html) - 结论依据:摘录中关于冗余情境需检查信息关系的定义、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:target domain separately. In the CD-CARS, the information gain measure is considered, selecting only the contextual attribute with the highest information gain. Only one context can be chosen for each dimension. For instance, suppose the day was pointed out as the attribute with the highest information gain, followed by DayType. The algorithm selects only the Day attribute since it encapsulates the same information in DayType.