Unsupervised learning - Wikipedia
5
公开标注数
5
参与人数
2026-07-28 10:02:53
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-28 13:23:53
原文高亮摘录
“An energy function is a macroscopic measure of a network's activation state.”
Whisper 随想笔记
Wait, so lower energy means better? That's like the opposite of what I'd expect from "energy".
划选高亮2026-07-28 13:14:53
原文高亮摘录
“An energy function is a macroscopic measure of a network's activation state.”
Whisper 随想笔记
So it's basically using physics jargon to describe how the network settles into a stable state. Cool.
划选高亮2026-07-28 10:20:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and…”
Whisper 随想笔记
I've seen this in image inpainting too, not just text. Same trick, different domain.
划选高亮2026-07-28 10:11:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and…”
Whisper 随想笔记
That's how they train those language models? Seems almost too simple to work that well.
划选高亮2026-07-28 10:02:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and…”
Whisper 随想笔记
So it's basically like playing a game of peek-a-boo with data, hiding a piece and making the model guess.
分享本页 Whisper
短链接
https://domwhisper.com/s/51574a9143d3嵌入代码
<iframe src="https://domwhisper.com/embed/51574a9143d3" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>