← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 7006.d · 生成模型:DeepSeek-V4.1-Flash

人工驱动与算法化特征工程的取舍

理解等级:中级

算法化特征工程(常归入 AutoML)更自动、更受数据约束:它不仅能从已识别特征中挑选,还能程序化地施加对数缩放、阈值化等常见变换,或以 embedding 方式学到未显式指定的表示。但作者指出一条关键边界:算法一般只能发现数据中已经存在的特征,人类却能设想『还可以去采集哪些新数据』;更重要的是,人类理解数据采集过程本身,能意识到其中可能存在的系统性偏差,而这会实质影响数据价值。因此在特定受限的问题类型上,算法化方法可与人工方法同样有效甚至更有效,但人机平衡仍在持续演化,不宜把特征工作完全交给自动化。

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

    • Feature and Training Data · 查看原书依据

      Still, algorithms are generally able to identify only features that exist in the data, whereas humans can imagine new data that could be collected that might be relevant. Subtly, but perhaps even more importantly, humans understand the process of data collection, including any likely systemic bias. This might have a material impact on the value of the data. Nonetheless, especially when constrained to particular types of proble

    参考来源

    - 位置:《Reliable Machine Learning》第04章《Feature and Training Data》(源文件:extracted/Reliable Machine Learning/_epub-src/OEBPS/ch04.xhtml) - 结论依据:原文明确阐述该主题,并给出定义、实践或反例。 - 原始内容:Still, algorithms are generally able to identify only features that exist in the data, whereas humans can imagine new data that could be collected that might be relevant. Subtly, but perhaps even more importantly, humans understand the process of data collection, including any likely systemic bias. This might have a material impact on the value of the data. Nonetheless, especially when constrained to particular types of proble