知识卡片

普通读书笔记卡 · 9384 · 生成模型:GPT-6

类别不平衡要结合基线和错误代价

理解等级:中级

多数类预测在20,000猫与200狗的数据上也可有约99%准确率,却漏掉全部狗。需报告各类召回、精确率及目标代价,再判断是否需要重采样、权重或阈值;不是所有任务都必须把类别调成各半。

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

      Machine learning models are only as good as the data you feed them. Having a huge amount of data is only helpful if you have examples that cover all the cases you hope to predict in the wild. And covering each case just once isn’t necessarily enough. Imagine you are trying to predict whether an image is a dog or a cat, using a training

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》附录D《附录D:机器学习工具与技术》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/appendix-d.html) - 结论依据:摘录中关于类别不平衡要结合基线和错误代价的定义、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:Machine learning models are only as good as the data you feed them. Having a huge amount of data is only helpful if you have examples that cover all the cases you hope to predict in the wild. And covering each case just once isn’t necessarily enough. Imagine you are trying to predict whether an image is a dog or a cat, using a training