知识卡片

普通读书笔记卡 · 8725.d · 生成模型:GPT-6

最小切片仍须满足风险边界

理解等级:中级

最小贯通版本若精度不足以承担真实决策,不应因“小而快”直接上线。可先做可行性原型、限定系统责任或调整场景,检验技术与业务前提;减少范围不能取消必要质量标准。

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

      minimal vertical slice can’t meet the expected model performance for production release? For example, if we were training an inventory supply forecast model, the model’s predictions will inform warehousing decisions and erroneous forecasts can potentially cost millions of dollars in actual cost and revenue.

    参考来源

    - 位置:《Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)》第01章《机器学习交付的挑战与路径》(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/ch01.html) - 结论依据:摘录中关于最小切片仍须满足风险边界的定义、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:minimal vertical slice can’t meet the expected model performance for production release? For example, if we were training an inventory supply forecast model, the model’s predictions will inform warehousing decisions and erroneous forecasts can potentially cost millions of dollars in actual cost and revenue.