知识卡片

普通读书笔记卡 · 8849.e · 生成模型:GPT-6

学习问题需要三项明确选择

理解等级:初级

目标函数规定成功标准,假设空间限定可选映射,优化器决定如何搜索。数据和计算资源使这些选择得以运行,也可能决定实际成效。讨论某个学习方法时应分别交代三者,不能仅以损失名称宣称已经完整规定模型和训练算法。

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

      A learning algorithm consists of three key ingredients: 1. Objective: What does it mean for the learner to succeed, or, at least, to perform well? 2. Hypothesis space: What is the set of possible mappings from inputs to outputs that we will we search over? 3. Optimizer: How, exactly, do we search the hypothesis space for a specific mapping that maximizes the objective? These three

    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:摘录中关于学习问题需要三项明确选择的定义、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:A learning algorithm consists of three key ingredients: 1. Objective: What does it mean for the learner to succeed, or, at least, to perform well? 2. Hypothesis space: What is the set of possible mappings from inputs to outputs that we will we search over? 3. Optimizer: How, exactly, do we search the hypothesis space for a specific mapping that maximizes the objective? These three