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.

2013 NIPS Proceedings – Advances in Neural Information Processing Systems

72 pointsby benhamnerover 11 years ago

6 comments

karpathyover 11 years ago
By the way, just this evening I formatted the accepted papers in a nicer way: (okay, I&#x27;m biased)<p><a href="http://cs.stanford.edu/people/karpathy/nips2013/" rel="nofollow">http:&#x2F;&#x2F;cs.stanford.edu&#x2F;people&#x2F;karpathy&#x2F;nips2013&#x2F;</a><p>The page allows you to toggle LDA topics and off to browse the papers, or (my personal favorite) find a paper you like and sort the other papers according to tf-idf similarity, which tends to reveal exceptionally relevant papers.
评论 #6818311 未加载
评论 #6819142 未加载
评论 #6819132 未加载
评论 #6818461 未加载
benhamnerover 11 years ago
This is an interesting case study in how the submitted headline affects the page&#x27;s rank on HN.<p>I&#x27;d originally submitted this earlier today, with the headline &quot;Neural Information Processing Systems (NIPS) 2013 Proceedings&quot;: <a href="https://news.ycombinator.com/item?id=6815771" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=6815771</a><p>It only got one other upvote and never made it to the front page. Meanwhile, another article submitted at almost exactly the same time with far less interesting content but a more provocative headline (on a user getting banned from Uber for API abuse) got ~15 votes, pushing it onto the front page.<p>I re-submitted this page with a slightly more descriptive (and buzzwordy) headline (&quot;State of the art Machine Learning papers: NIPS 2013&quot;), and it almost immediately ended up on the front page. Since then the headline has been reverted to the page&#x27;s headline, again slowing the rate at which it&#x27;s received votes.
评论 #6817822 未加载
ajtullochover 11 years ago
Alexandre Passos has an excellent editorial selection of NIPS 2013 papers (along with some comments) on his blog at [1].<p>[1]: <a href="http://atpassos.me/post/67560831508/nips-2013-reading-list" rel="nofollow">http:&#x2F;&#x2F;atpassos.me&#x2F;post&#x2F;67560831508&#x2F;nips-2013-reading-list</a>.
djuliusover 11 years ago
Now the game is : Among these tons of (bad&#x2F;good) applied mathematics , find the maybe existing one paper that will : - Have a real world application - Go through the years<p>More difficult : only by reading titles.
评论 #6818484 未加载
prestyover 11 years ago
while we&#x27;re at it, here&#x27;s from ICML2013<p><a href="http://icml.cc/2013/?page_id=47" rel="nofollow">http:&#x2F;&#x2F;icml.cc&#x2F;2013&#x2F;?page_id=47</a> (click on the schedule images)
评论 #6817659 未加载
评论 #6817658 未加载
seijiover 11 years ago
Now prove each of those titles isn&#x27;t auto-generated by the HN headline generator.