/sci/ - Science & Math » Thread #11077421

191KiB, 1080x924, 1571597559970.jpg

View Same Google iqdb SauceNAO

Anonymous Sun 20 Oct 19:00:21 2019 No.11077421 View Reply Original Report

Quoted By: >>11077452 >>11077558

>The next evolution in artificial intelligence may be a matter of dispensing with all the probabilistic tricks of deep learning, mastering instead a manifold of shifting energy values, according to deep learning's pied piper, Yann LeCun

Is the AI community going full retard?

Anonymous

Anonymous Sun 20 Oct 2019 19:13:02 No.11077452 Report

Quoted By: >>11077463

>>11077421
What did LeCun even do?
Deep learning was just the next logical step after the failure of basic perceptrons and the increase in both computational power and available data.
A third AI winter can't come soon enough to shut their stupid mouth.
The next advance in AI will come from people actually trying to understand and classify parts of the human brain and actually merging the connectionism to the symbolism approache.

Anonymous

Anonymous Sun 20 Oct 2019 19:16:38 No.11077463 Report

Quoted By: >>11077468 >>11077508 >>11077577

>>11077452
>The next advance in AI will come from people actually trying to understand and classify parts of the human brain and actually merging the connectionism to the symbolism approache
Thats where neural-nets came from in the first place and people still have pretty much have no fucking clue what's going on in even basically applications of them much less the human brain
Neuro-science will never be worth anything because the brain is end to end hidden layers

Anonymous

Anonymous Sun 20 Oct 2019 19:17:41 No.11077468 Report

Quoted By:

>>11077463
*even basic

Anonymous

Anonymous Sun 20 Oct 2019 19:35:39 No.11077508 Report

Quoted By:

>>11077463
It might seem hard, even impossible, but I'm convinced it's the only way out, if we are to emulate the human mind.
No one said that intelligence could be reduced to a few mathematical concepts.
Gradient descent can only do so much.
We actually have to get our hands dirty now that all the low hanging fruit have been picked.

Anonymous

Anonymous Sun 20 Oct 2019 19:51:26 No.11077558 Report

Quoted By: >>11077690

>>11077421
He's talking about EBMs, some research he did about a decade ago that's getting some more attention recently.

http://yann.lecun.com/exdb/publis/pdf/lecun-06.pdf

https://openai.com/blog/energy-based-models/

Anonymous

Anonymous Sun 20 Oct 2019 19:58:12 No.11077577 Report

Quoted By: >>11077585

>>11077463
You ever seen a fly get stuck in an infinite loop until it exhausts all its resources trying to exit through a closed window? That's millions of years of evolution, which if 'product-itized' in its current form would have the Youtubosphere pissed off that their gay new drone keeps running out of batteries trying to find a way through glass.

Anonymous

Anonymous Sun 20 Oct 2019 20:01:20 No.11077585 Report

Quoted By:

>>11077577
attach gun to drone
have it shoot at air if it can't get out

Anonymous

Anonymous Sun 20 Oct 2019 20:47:23 No.11077690 Report

Quoted By: >>11077794

>>11077558
If this is about using energy as the objective function instead of quadratic loss, I've spoken to CERN researchers who tested both and came to the conclusion that using energy is inferior in many ways.

Anonymous

Anonymous Sun 20 Oct 2019 21:24:43 No.11077794 Report

Quoted By: >>11077836

>>11077690
In what sense is it inferior? Don't really know anything about EBMs, but their concept seems cool.

Anonymous

Anonymous Sun 20 Oct 2019 21:39:41 No.11077836 Report

Quoted By: >>11077867

>>11077794
Worse prediction quality and lesser generalization capability. They said they reached higher scores with the standard approach, although apparently it wasn't extremely much.

I also guess implementation is a bitch since you have to derive with respect to your inputs.

Anonymous

Anonymous Sun 20 Oct 2019 21:53:48 No.11077867 Report

Quoted By:

>>11077836
Now that I've read part of the OpenAI paper it seems they still aren't as powerful as GANs for image processing, but it seems like they're almost getting there. Well, we'll see, who knows.

Capcode	All Only User Posts Only Moderator Posts Only Admin Posts Only Developer Posts
Show Posts	All Only With Images Only Without Images
Deleted Posts	All Only Deleted Posts Only Non-Deleted Posts
Ghost Posts	All Only Ghost Posts Only Non-Ghost Posts
Post Type	All Only Sticky Threads Only Opening Posts Only Reply Posts
Results	All Grouped By Threads
Order	Latest Posts First Oldest Posts First

Your latest searches