← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9260.c · 生成模型:GPT-6

多次挑选会消耗验证集独立性

理解等级:中级

验证集不直接反向求梯度,仍可通过架构、超参数和停止选择影响最终模型。反复比较后其最佳成绩可能乐观,不能称天然无偏;最终保留数据用于选择结束后的独立估计。

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

      Loss computation: a loss function is used to compute the error between the model’s predictions and the ground truth values (a more detailed discussion of loss functions is presented below). In this training stage, the loss (error) is computed on the training set and the validation set. Since the validation set is not used directly to update the model parameters over iterations, it provides an

    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:摘录中关于多次挑选会消耗验证集独立性的定义、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:Loss computation: a loss function is used to compute the error between the model’s predictions and the ground truth values (a more detailed discussion of loss functions is presented below). In this training stage, the loss (error) is computed on the training set and the validation set. Since the validation set is not used directly to update the model parameters over iterations, it provides an - 外部纠错依据(2026-11-06核验):https://scikit-learn.org/stable/modules/cross_validation.html;仅用于限定原书错误,不替代本卡原书出处。