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.

Deep Learning Is Easy – Learn Something Harder

67 pointsby hlynurdover 1 year ago

8 comments

jph00over 1 year ago
IMO this 2016 article really hasn&#x27;t aged well. It turned out that architectural improvements really did matter, and there was still loads of low-hanging fruit. His prediction that bayesian approaches (which were the topic of his PhD) would turn out to be fundamental, has not turned out to be true so far (although they do have their place).<p>(I think in general when people say that their special area of study is particularly important, it should be taken with a grain of salt!)
评论 #37413975 未加载
light_hue_1over 1 year ago
This is terrible and frankly self serving advice.<p>&quot;Don&#x27;t build on top of deep learning. Build on top of MCMC-like methods&quot;<p>I used to do research into such methods. That game is over. It&#x27;s a massive waste of time at the moment. The whole idea is how do we import what was good about those methods into the modern deep learning toolkit. How do I sample from distribution with dl? How do I get uncertainty estimates? How do I compose models, get disentangled representations, get few shot learning, etc.<p>The idea that people should go back to tools like MCMC today is pretty absurd. That entire research program was a failure and never scaled to anything. I say this of my many dozens of papers in the area too.<p>I would never give this advice to my PhD students.<p>Maybe in a decade or two someone will rescue MCMC like methods. In the meantime your PhD students will suffer by being irrelevant and having skills that no one needs.
评论 #37412186 未加载
dbmikusover 1 year ago
My general belief, is that the best way to learn at the frontier of something is to pick a problem or a goal and try to solve it. Then you will learn what is in the way of getting that done.<p>Unless you already have deep expertise, I think it&#x27;s a bad idea to pick a research area and just go and research that. You won&#x27;t have intuition about why it&#x27;s a good thing to research. However, you can have intuition about real world problems and the solutions you want to see, and then work backwards to what you need to research.
评论 #37412133 未加载
评论 #37415562 未加载
评论 #37413545 未加载
blind666over 1 year ago
It is interesting to look back and evaluate the preferences &#x2F; intuitions prominent researchers had in the field (most of whom started their careers experimenting with MNIST-scale of data, at best)<p>With access to unfathomable amounts of data, especially over the last couple of years, the game changed entirely and is not seeming to cool down anytime soon.<p>The field, certainly, values engineering a lot more than it used to, and it is exciting to see how major advances together with open-source contributions are going to take us
评论 #37412562 未加载
评论 #37412378 未加载
danielmarkbruceover 1 year ago
Maybe if you stick to purely theoretical stuff, it&#x27;s easy. Actually building real systems that work and add value using deep learning isn&#x27;t easy. There are so many gotchas.
hedgehog0over 1 year ago
<a href="https:&#x2F;&#x2F;www.inference.vc&#x2F;we-may-be-surprised-again&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.inference.vc&#x2F;we-may-be-surprised-again&#x2F;</a><p>The author wrote this article one month ago, and he mentioned where he thought wrong about DL
jacobnover 1 year ago
[2016]
评论 #37412214 未加载
sullyj3over 1 year ago
Pretty straightforward case of the curse of knowledge (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Curse_of_knowledge" rel="nofollow noreferrer">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Curse_of_knowledge</a>), in my opinion.