知识卡片
预测反馈可能固化已有偏差
模型行为会改变真实环境及能收集的数据,下一轮再用这些数据训练可能强化原偏差。应区分外部结果与被系统决策影响的结果,监控选择效应和恶意反馈;数据更多不保证信息更客观。
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
原书出处 · 1 处
- · 查看原书依据
When collecting natural labels, we must also consider how to mitigate the risks of data poisoning attacks (more on this shortly) and dangerous runaway feedback loops, where the model’s biased predictions have an effect on the real world, which further entrenches the bias in the data and subsequent models.
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:摘录中关于预测反馈可能固化已有偏差的定义、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:When collecting natural labels, we must also consider how to mitigate the risks of data poisoning attacks (more on this shortly) and dangerous runaway feedback loops, where the model’s biased predictions have an effect on the real world, which further entrenches the bias in the data and subsequent models.