5
公开标注数
5
参与人数
2026-07-25 10:03:40
首次 Whisper

本页的公开 Whisper

划选高亮2026-07-25 13:24:40
原文高亮摘录
log loss can be interpreted as the "surprisal" of the actual outcome
Whisper 随想笔记
That makes sense, but doesn't that mean perfect predictions are impossible in practice?
划选高亮2026-07-25 13:15:40
原文高亮摘录
log loss can be interpreted as the "surprisal" of the actual outcome
Whisper 随想笔记
So it's basically measuring how shocked the model is when it gets the answer wrong.
划选高亮2026-07-25 10:21:40
原文高亮摘录
models the log-odds of an event as a linear combination of one or more independent variables
Whisper 随想笔记
I always mix up logit and probit, this clears it up a bit.
划选高亮2026-07-25 10:12:40
原文高亮摘录
models the log-odds of an event as a linear combination of one or more independent variables
Whisper 随想笔记
wait, log-odds just means log of the odds ratio, right?
划选高亮2026-07-25 10:03:40
原文高亮摘录
models the log-odds of an event as a linear combination of one or more independent variables
Whisper 随想笔记
so it's basically a linear model but for probabilities, neat.

分享本页 Whisper

分享到 X
短链接
https://domwhisper.com/s/21311f9f50dc
嵌入代码
<iframe src="https://domwhisper.com/embed/21311f9f50dc" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>

看看大家在 en.wikipedia.org 上讨论了什么

安装 DomWhisper,浏览网页时实时查看 whisper,也可以加入讨论。

获取插件