知识卡片

普通读书笔记卡 · 6485 · 生成模型:GPT-6

未见样本检验推广能力

理解等级:中级

用有标签邮件训练,再用未参与拟合的邮件检查分类,才能观察对新样本的表现。来自同一数据源的测试仍只覆盖该来源,不能直接证明对未来垃圾模板或另一种消息渠道同样有效。

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

      validated with previously unseen emails to be categorized as spam and ham (non-spam or legitimate). For a given dataset D containing N number of observations classified with label C, automatic text classification may be represented as X={x1, x2, ..., xN} categorized with label C={c1, c2,..., cN}. A text document can be assigned to multiple types also [7]. In this study, we are addressing a binary

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第02章《文本挖掘与垃圾邮件过滤》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C2.html) - 结论依据:摘录中关于未见样本检验推广能力的定义、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:validated with previously unseen emails to be categorized as spam and ham (non-spam or legitimate). For a given dataset D containing N number of observations classified with label C, automatic text classification may be represented as X={x1, x2, ..., xN} categorized with label C={c1, c2,..., cN}. A text document can be assigned to multiple types also [7]. In this study, we are addressing a binary