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

Self-supervised learning: The dark matter of intelligence

ai.facebook.com

Post reply on HN
Print view View original

41–50 of 76 posts

Re: Self-supervised learning: The dark matter of intelligence

#41

Post by elcomet »

uoaei wrote: post #34
visarga wrote: post #20

Earlier quoted context omitted.

> How do you understand what the model has learned? How do you do that with humans? You watch their behavior, language and you test them.

Humans can explain their reasoning when you ask them. The best we have with NNs is a fancy version of first-order sensitivity analysis.

Humans cannot really explain their reasoning. It has been shown that they usually invent an explanation that matches what has already been decided in their black-box.They mostly use post-hoc explanation, but cannot explain the true decision mechanism.

If you make them believe that they choose another decision, they will create another explanation on the fly.

Re: Self-supervised learning: The dark matter of intelligence

#42

Post by jtsiskin »

just1morething wrote: post #19

If you cut some words out of a newspaper and a person writes words in those blanks then what has happened? If we cut out parts of a painting and a person paints in those blanks then what has happened? How is the person who wrote in the blanks or the person who painted in the blanks changed by writing or painting in the blanks? How are they changed when someone responds to what they've written or painted? How did the…

The person isn’t changed, just like the weights aren’t changed. You’re missing the training step - after the person fills in the blank, then we tell them what was supposed to go in the blank. If I had you try to paint the the rest of the face of a portrait, you may do a poor job, but then if I showed you exactly what it was supposed to look like, you can see what you did wrong, and next time you will draw it better.

Re: Self-supervised learning: The dark matter of intelligence

#43

Post by elcomet »

Reebz wrote: post #13

State of the art performance is being broken in multiple fields rapidly these days. However, AI explainability has a long way to go. Scaling opaqueness makes this problem worse. Fine tuning labels black-box style is a terrifying concept to most who are working in fields where great risk must be managed to avoid unintended and disparate impact. Facebook making an oopsies suggesting my friends face in a photo instead o…

I don't really agree with you.

> If you were rejected by a bank for a home loan, you would want to know why your creditworthiness wasn’t evaluated positively (and banks must explain precisely why to regulators).

This is why we don't use humans to evaluate credits, but precise algorithms. Humans are just applying the algorithms, they are not evaluating themselves with their gut feeling. I don't see why this would change with AI. Regulations prevents unexplainable tools to be used there, so deep learning black box models will not be used, similarly to why humans are not used today.

But in cases where performance is required, but not explainability, then deep learning will strive. And I believe that cases where explanation is required is only a very small subset of areas where AI could be useful.

> And if a self-driving car made a decision in a collision

Would you prefer a car that crashes once every 100 million miles but is not explainable, or a car that crashes once every 100 miles but is interpretable can explain why it crashed ?

Re: Self-supervised learning: The dark matter of intelligence

#44

Post by jtsiskin »

ilaksh wrote: post #27

Self-supervised learning is very promising. But it is strange to me that so much computer vision research has no mention of the 3d structure of objects. That's why I like things like this https://arxiv.org/abs/2102.12627 "How to represent part-whole hierarchies in a neural network" by Hinton.

Yeah, humans don’t learn from still pictures, we see things moving through time and space and rotating. This is likely providing us with essentially a lot of “self supervised” data. For instance https://www.ted.com/talks/pawan_sinha_how_brains_learn_to_se... starting at 8:11

Re: Self-supervised learning: The dark matter of intelligence

#45

Post by a_imho »

visarga wrote: post #24
Reebz wrote: post #13

State of the art performance is being broken in multiple fields rapidly these days. However, AI explainability has a long way to go. Scaling opaqueness makes this problem worse. Fine tuning labels black-box style is a terrifying concept to most who are working in fields where great risk must be managed to avoid unintended and disparate impact. Facebook making an oopsies suggesting my friends face in a photo instead o…

High risk models should work with humans in the loop, not autonomous.

Would this rule out self driving cars from the get go?

Re: Self-supervised learning: The dark matter of intelligence

#46

Post by desku »

Schiphol wrote: post #36
knuthsat wrote: post #35

Earlier quoted context omitted.

Tools for exploring the models are already being developed. Language models that are not given concepts of part-of-speech, dependency trees, grammars, develop representations of their own and people have found ways to inspect them.

Could you please provide pointers to relevant papers? I'm very interested.

Here's a paper on how BERT (a large Transformer model trained using self-supervised learning) implicitly learns the traditional NLP pipeline: https://arxiv.org/abs/1905.05950

Re: Self-supervised learning: The dark matter of intelligence

#47

Post by ilaksh »

jtsiskin wrote: post #44
ilaksh wrote: post #27

Self-supervised learning is very promising. But it is strange to me that so much computer vision research has no mention of the 3d structure of objects. That's why I like things like this https://arxiv.org/abs/2102.12627 "How to represent part-whole hierarchies in a neural network" by Hinton.

Yeah, humans don’t learn from still pictures, we see things moving through time and space and rotating. This is likely providing us with essentially a lot of “self supervised” data. For instance https://www.ted.com/talks/pawan_sinha_how_brains_learn_to_se... starting at 8:11

Great video. It's interesting to see how far semantic segmentation has progressed since 2009.

Re: Self-supervised learning: The dark matter of intelligence

#48

Post by TheOtherHobbes »

epidemian wrote: post #14
tasogare wrote: post #9

Earlier quoted context omitted.

> Sure, but humans are a relatively known entity. We don’t know how brain works, why sleep exist, most of humans cultures and languages are not documented, hundreds if not thousands of psychological and medical things are unknown, etc. Machines and their applications are a few more magnitudes more understood than any human matter, by the sheer fact we created them. Their complexity is ridiculously low in comparison t…

on one hand i agree with what you're saying. we humans have done terrible stuff like wars, genocides, famines, destruction of ecosystems, extinction of entire species, etc. and that's only the things we did more or less deliberately. we might cause our own extermination or a mass extinction event "by mistake", and we don't even understand how basic parts of our minds work. but all of that being said, i think it's als…

This already applies to corporations.

AI is just the fruiting body of something that has already happened.

Re: Self-supervised learning: The dark matter of intelligence

#49

Post by minikites »

pablovidal85 wrote: post #16
minikites wrote: post #8

Earlier quoted context omitted.

Very few individual humans can act in a way that affects hundreds of millions of people, computers can do that in a nanosecond.

Can't humans with computers affect hundreds of millions of people too?

Only with the computer's help, that's my point.

Re: Self-supervised learning: The dark matter of intelligence

#50

Post by TheOtherHobbes »

elcomet wrote: post #43
Reebz wrote: post #13

State of the art performance is being broken in multiple fields rapidly these days. However, AI explainability has a long way to go. Scaling opaqueness makes this problem worse. Fine tuning labels black-box style is a terrifying concept to most who are working in fields where great risk must be managed to avoid unintended and disparate impact. Facebook making an oopsies suggesting my friends face in a photo instead o…

I don't really agree with you. > If you were rejected by a bank for a home loan, you would want to know why your creditworthiness wasn’t evaluated positively (and banks must explain precisely why to regulators). This is why we don't use humans to evaluate credits, but precise algorithms. Humans are just applying the algorithms, they are not evaluating themselves with their gut feeling. I don't see why this would chan…

Isn't it interesting that an industry like banking, built on those beautiful, precise algorithms, blows up so regularly?
Post reply on HN