知识卡片
经验风险只度量训练样本平均
经验风险最小化在给定假设空间中,选择使训练集平均损失最小的函数:min_f (1/N)ΣL(f(xᵢ),yᵢ)。经验分布上的最优不自动等于真实分布上的最优,因此仍需独立评估泛化;样本量、抽样方式和模型容量都影响差距。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 学习导论
原书出处 · 1 处
- · 查看原书依据
the last section can be formalized using the framework of empirical risk minimization (ERM). This framework applies specifically to the supervised setting where we are learning a function that predicts y from x given many training examples . The idea is to minimize the average error (i.e., risk) we incur over all the training data (i.e., empirical distribution). The ERM problem is stated as follows:
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第09章《学习导论》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c009b.xhtml)
- 结论依据:摘录中关于经验风险只度量训练样本平均的定义、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:the last section can be formalized using the framework of empirical risk minimization (ERM). This framework applies specifically to the supervised setting where we are learning a function that predicts y from x given many training examples . The idea is to minimize the average error (i.e., risk) we incur over all the training data (i.e., empirical distribution). The ERM problem is stated as follows: