Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

“Deep Learning has outlived its usefulness as a buzz-phrase”

facebook.com

Post reply on HN
Print view View original

31–40 of 107 posts

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#31

Post by grzm »

make3 wrote: post #29
danbmil99 wrote: post #6

"See more of Yann LeCun on Facebook" popup, no access to the page. No, I don't want to create a Facebook account to read a blog post. Perhaps links to walled-garden pages where you need an account and need to be logged in should be prohibited or at least discouraged.

this will get downvoted as all held, but I really think most socially apt people should have Facebook accounts these days

> "this will get downvoted as all [hell], but"

It'll have a better chance of avoiding down votes if you leave this out. It's against the guidelines:

> "Please don't comment about the voting on comments. It never does any good, and it makes boring reading."

https://news.ycombinator.com/newsguidelines.html

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#32

Post by etrautmann »

make3 wrote: post #29
danbmil99 wrote: post #6

"See more of Yann LeCun on Facebook" popup, no access to the page. No, I don't want to create a Facebook account to read a blog post. Perhaps links to walled-garden pages where you need an account and need to be logged in should be prohibited or at least discouraged.

this will get downvoted as all held, but I really think most socially apt people should have Facebook accounts these days

It’s still reasonable to push discussions away from FB and walled gardens in general.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#33

Post by tedivm »

kinkrtyavimoodh wrote: post #18
danbmil99 wrote: post #6

"See more of Yann LeCun on Facebook" popup, no access to the page. No, I don't want to create a Facebook account to read a blog post. Perhaps links to walled-garden pages where you need an account and need to be logged in should be prohibited or at least discouraged.

I opened it in an Incognito window and it worked fine. Public posts on FB can be seen without logging in.

How long did you wait on the page? At first when it loads you can read it just fine, but then an obnoxious pop up appears. There is a little "not now" link on the bottom that will get you back to the post, but I can see how someone would miss that (it's a great example of a bad UI).

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#34

Post by BucketSort »

seanmcdirmid wrote: post #30
BucketSort wrote: post #19

I believe this paper by Marcus ( https://arxiv.org/ftp/arxiv/papers/1801/1801.00631.pdf ) earlier this week inspired this. Edit: I don't mean Marcus inspired the term differentiable programming; he inspired LeCun to emphasize the wider scope of deep learning after Marcus attacked it. In fact, LeCun liked a post on twitter rebutting Marcus' paper that also talks about differentiable programming: https://twitter.com/td…

Or the other way around... He has been throwing around the term for awhile now.

It was most certainly the other way around. Marcus does not focus on differentiable programming in his paper. See my edit.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#35

Post by bra-ket »

rememberlenny wrote: post #3

[Text from post] OK, Deep Learning has outlived its usefulness as a buzz-phrase. Deep Learning est mort. Vive Differentiable Programming! Yeah, Differentiable Programming is little more than a rebranding of the modern collection Deep Learning techniques, the same way Deep Learning was a rebranding of the modern incarnations of neural nets with more than two layers. But the important point is that people are now build…

it's really a pity that after 75 years of AI research the best thing we've got is still based on gradient descent, a brute force trial and error.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#36

Post by kweinber »

make3 wrote: post #29
danbmil99 wrote: post #6

"See more of Yann LeCun on Facebook" popup, no access to the page. No, I don't want to create a Facebook account to read a blog post. Perhaps links to walled-garden pages where you need an account and need to be logged in should be prohibited or at least discouraged.

this will get downvoted as all held, but I really think most socially apt people should have Facebook accounts these days

“most socially apt people should have Facebook accounts”

This is like saying that most people who know a lot about food should regularly visit McDonalds since it is the most eaten-at restaurant.

I would venture the opposite, people who are socially apt and attuned are probably least likely to be on Facebook... they’ve likely learned enough about it to stay far, far, away.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#37

Post by rspeer »

username223 wrote: post #13
oh-kumudo wrote: post #7

Just a rebranding, though necessary one. Deep Learning is not really all about 'deep' anymore, many successful models don't really need a lot of layers.

So it's still just neural nets? Cool -- we've seen that before.

Is a single SGD layer a neural net? Is an image filter or an audio filter a neural net? Is matrix multiplication a neural net? This would strain the intended definition even farther than it's already been strained.

But all of those are differentiable programming, and rightly so because they're all pieces that you use and compose together to make interesting learning mechanisms, including the ones that we vaguely refer to as "deep learning" now.

I like the terminology. It's not about what the original long-abandoned motivation for the design was ("neural"). It's not about how gratuitously complex you can make it ("deep"). "Differentiable" is about how it works and how we design it.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#38

Post by BucketSort »

You may have seen DeepMind's results last year where it trained 3D models to move through space in different ways, entitled "Emergence of Locomotion Behaviours in Rich Environments" ( https://arxiv.org/pdf/1707.02286.pdf , https://www.youtube.com/watch?v=hx_bgoTF7bs&feature=youtu.be). If you have a look in the paper, the method they use "Proximal Policy Optimization" is a great example of differentiable programming that does not include a neural network. I actually realized this last month when I was preparing a talk on deep learning, because I thought it used deep neural nets in its application, but found that it didn't.

Re: “Deep Learning has outlived its usefulness as a buzz-phrase”

#40

Post by log_base_login »

bra-ket wrote: post #35
rememberlenny wrote: post #3

[Text from post] OK, Deep Learning has outlived its usefulness as a buzz-phrase. Deep Learning est mort. Vive Differentiable Programming! Yeah, Differentiable Programming is little more than a rebranding of the modern collection Deep Learning techniques, the same way Deep Learning was a rebranding of the modern incarnations of neural nets with more than two layers. But the important point is that people are now build…

it's really a pity that after 75 years of AI research the best thing we've got is still based on gradient descent, a brute force trial and error.

As much of a pity that, 70 years later, we are still using transistor based computers originally derived from three wires stuck in a piece of rock[1] by some very innovative fellows at Bell Labs[2]?

[1]http://images.computerhistory.org/revonline/images/500004836... [2]http://www.computerhistory.org/revolution/digital-logic/12/2...

Post reply on HN