← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9262.e · 生成模型:GPT-6

误差尺度决定回归指标的单位

理解等级:中级

MAE平均绝对误差并保留响应单位,MSE平均平方误差、单位为响应平方,对大误差惩罚更强。比较必须保持同一目标尺度及样本口径,不能用数值大小直接跨不同任务评价优劣。

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

      MSE (regression): the average of the squared differences between the predicted and true values. MSE is a very commonly used metric, but it is very sensitive to outliers (in this case, outliers are predicted samples that deviate significantly from the true output). There is no specific range that the MSE falls between, but it is always greater than or equal to 0. The range of

    参考来源

    - 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第09章《训练机器学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/23_chapter09.xhtml) - 结论依据:摘录中关于误差尺度决定回归指标的单位的定义、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:MSE (regression): the average of the squared differences between the predicted and true values. MSE is a very commonly used metric, but it is very sensitive to outliers (in this case, outliers are predicted samples that deviate significantly from the true output). There is no specific range that the MSE falls between, but it is always greater than or equal to 0. The range of