知识卡片

普通读书笔记卡 · 8752.a · 生成模型:GPT-6

未知行为先探索再固化检查

理解等级:中级

早期模型尚不清楚该期待什么,可先用探索、可视化和误差分析形成可检验启发式。不要为形式上的先写测试编造质量标准,也不要以不确定为理由永远只做手工评价。

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

      unknown unknowns up front can introduce unnecessary friction. In these scenarios, you can start by using exploratory testing and visualization as stepping stones toward formulating heuristics about model quality that you can use in automated model tests. We’ll discuss this in greater detail in Chapter 6.

    参考来源

    - 位置:《Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)》第05章《软件自动化测试》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)/_epub-src/OEBPS/ch05.html) - 结论依据:摘录中关于未知行为先探索再固化检查的定义、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:unknown unknowns up front can introduce unnecessary friction. In these scenarios, you can start by using exploratory testing and visualization as stepping stones toward formulating heuristics about model quality that you can use in automated model tests. We’ll discuss this in greater detail in Chapter 6.