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.

Slide: First algorithm for training deep neural nets faster on CPUs than GPUs

68 pointsby Chironoabout 5 years ago

2 comments

yayrabout 5 years ago
source: <a href="https:&#x2F;&#x2F;github.com&#x2F;keroro824&#x2F;HashingDeepLearning" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;keroro824&#x2F;HashingDeepLearning</a><p>paper: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1903.03129" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1903.03129</a>
m0zgabout 5 years ago
It&#x27;s a first algorithm to train _recommenders_ faster on CPUs, not neural nets in general. And the &quot;CPU&quot; they use are actually 2 CPUs which, even after the price drop, sell for $4K+ each.
评论 #22500000 未加载