[1611.01578] Neural Architecture Search with Reinforcement Learning
6
公开标注数
6
参与人数
2026-07-24 09:42:56
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-24 16:06:56
原文高亮摘录
“arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.”
Whisper 随想笔记
Cool, so they're basically opening up the platform for community-built tools now.
划选高亮2026-07-24 13:03:56
原文高亮摘录
“Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)”
Whisper 随想笔记
Why do they always list subjects like that? Just pick one, arxiv.
划选高亮2026-07-24 12:54:56
原文高亮摘录
“Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)”
Whisper 随想笔记
These three categories never surprise me, NAS always hits all of them.
划选高亮2026-07-24 10:00:56
原文高亮摘录
“Neural networks are powerful and flexible models that work well for many difficult learning tasks”
Whisper 随想笔记
Couldn't agree more, especially when you see what they do for image tasks these days.
划选高亮2026-07-24 09:51:56
原文高亮摘录
“Neural networks are powerful and flexible models that work well for many difficult learning tasks”
Whisper 随想笔记
Powerful yes, but flexible? I've spent weeks tuning architectures that felt anything but flexible.
划选高亮2026-07-24 09:42:56
原文高亮摘录
“Neural networks are powerful and flexible models that work well for many difficult learning tasks”
Whisper 随想笔记
True, but the hard part is still designing them, which is what this paper tackles.
分享本页 Whisper
短链接
https://domwhisper.com/s/d98f96737ca8嵌入代码
<iframe src="https://domwhisper.com/embed/d98f96737ca8" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>