TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: What are some of the best papers on AI, ML, DL and their applications?

53 pointsby noob_engalmost 2 years ago
I was reading the Deep Double Descent paper by OpenAI: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1912.02292" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1912.02292</a>. The writing is so lucid. Even the structure of the paper is non-conventional. They have a results section before the Related Works section to give sneak peak of what the paper is about. More like telling a story. Even before starting the Introduction there is a self explanatory image spanning the entier two columns.<p>Can you link to more papers that are written in such style and are easy to read if you have the background knowledge?

4 comments

idorosenalmost 2 years ago
The paper introducing support vector machines by Cortes &amp; Vapnik was written exceptionally well in my opinion. It tells a part of the story of 60 years of pattern recognition (ML) succinctly from Fisher in 1936 to 1992.<p><a href="https:&#x2F;&#x2F;link.springer.com&#x2F;content&#x2F;pdf&#x2F;10.1007&#x2F;bf00994018.pdf" rel="nofollow">https:&#x2F;&#x2F;link.springer.com&#x2F;content&#x2F;pdf&#x2F;10.1007&#x2F;bf00994018.pdf</a>
ftxbroalmost 2 years ago
A Mathematical Theory of Communication by Claude Shannon (<a href="https:&#x2F;&#x2F;people.math.harvard.edu&#x2F;~ctm&#x2F;home&#x2F;text&#x2F;others&#x2F;shannon&#x2F;entropy&#x2F;entropy.pdf" rel="nofollow">https:&#x2F;&#x2F;people.math.harvard.edu&#x2F;~ctm&#x2F;home&#x2F;text&#x2F;others&#x2F;shanno...</a>)
评论 #36092874 未加载
flor1salmost 2 years ago
I&#x27;m not sure if it&#x27;s truly a timeless paper, but &quot;Attention is all you need&quot; by Vaswani et al. has been super influential in recent years. Also &quot;Deep Unsupervised Learning using Nonequilibrium Thermodynamics&quot; by Sohl-Dickstein et al. (about Diffusion Models) and &quot;NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis&quot; by Mildenhall et al. were hugely influential to me.
gverrialmost 2 years ago
<a href="https:&#x2F;&#x2F;paperswithcode.com" rel="nofollow">https:&#x2F;&#x2F;paperswithcode.com</a>