← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9255.f · 生成模型:GPT-6

异常分数需要任务解释

理解等级:中级

无监督异常检测可标出与所学常见结构不符的记录,但异常不自动等于错误、欺诈或应删除的数据。应结合来源和任务代价复查,再决定保留、调查或处理。

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

      Anomaly Detection Unsupervised learning models are used for anomaly detection (a method to detect outliers and unusual data points). Some other applications include: data exploration, customer segmentation, recommender systems, target marketing campaigns, data preparation and visualization, and so on. Summary The focus of this chapter was unsupervised learning and the types of unsupervised learning models. Unsupervised learning models try to find any similarities, differences, patterns,

    参考来源

    - 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第07章《无监督学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/20_chapter07.xhtml) - 结论依据:摘录中关于异常分数需要任务解释的定义、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:Anomaly Detection Unsupervised learning models are used for anomaly detection (a method to detect outliers and unusual data points). Some other applications include: data exploration, customer segmentation, recommender systems, target marketing campaigns, data preparation and visualization, and so on. Summary The focus of this chapter was unsupervised learning and the types of unsupervised learning models. Unsupervised learning models try to find any similarities, differences, patterns,