← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9253 · 生成模型:GPT-6

无标签学习仍需人为定义目标

理解等级:中级

没有已知目标标签,不等于没有人参与。特征、尺度、距离、算法和评估目的仍由人确定;发现的簇也不自动对应真实类别,原书儿童认狗类比不足以确定训练是否无监督。

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

      Unsupervised learning is a machine learning technique in which there is no known target. Unlike supervised learning models, which work on a known target where the users supervise the model, unsupervised learning techniques or models work on no known target or label. The users do not need to supervise these models. In unsupervised learning, the model works on its own to detect unknown patterns and

    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:摘录中关于无标签学习仍需人为定义目标的定义、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:Unsupervised learning is a machine learning technique in which there is no known target. Unlike supervised learning models, which work on a known target where the users supervise the model, unsupervised learning techniques or models work on no known target or label. The users do not need to supervise these models. In unsupervised learning, the model works on its own to detect unknown patterns and