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

Yann LeCun's comment on AlphaGo and true AI

facebook.com

Post reply on HN
Print view View original

191–200 of 216 posts

Re: Yann LeCun's comment on AlphaGo and true AI

#191

Post by scotty79 »

woko wrote: post #118
scotty79 wrote: post #117

> As I've said in previous statements: most of human and animal learning is unsupervised learning. I don't think that's true. When baby is learning to use muscles of its hands to wave them around there's no teacher to tell it what should its goal be. But physics and pain teaches it fairly efficiently which moves are bad idea. It has built in face detection engine and the orienting and attempting to move and reach tow…

Sorry but what you describe is not what supervised learning means. It has a specific meaning in AI. At best, what you describe is reinforcement learning. And I don't think this is how we learn to recognize people's faces.

I'm not sure if supervised learning is such a narrow term but I'll take your word for it. As for recognizing faces

I think we have that pretty much baked in the hardware. Faces are recognized immediately and not just by humans, also animals. I think people who lost ability to see faces, can't re-learn it.

Re: Yann LeCun's comment on AlphaGo and true AI

#192

Post by sabertoothed »

emcq wrote: post #173
sabertoothed wrote: post #153

Earlier quoted context omitted.

I feel that your analogy does not disprove OP's claim. You would first have to prove that the analogy is actually applicable. Theoretically, one could argue that motion is substantially different from intelligence such that the analogy does not hold. But I am with you in that engineering / CS / ... should not wait for neuroscience to make further discoveries but continue the journey.

Interesting point, but which do you think is a more reasonable prior: that intelligence is a deterministic process similar other's we've encountered or that there is something uniquely different about intelligence than other physical phenomena? I think the latter requires more assumptions so I would argue philosophically it is the one that requires the proof or more evidence :) Regardless, my feeling is that there is…

I did not mean to have implied that I think there is anything magical about intelligence. Of course, it is based on physical phenomena. I am doing my PhD right now and I try to incorporate as much AI/ML into it as possible.

What I meant to say is that our ANNs are so ridiculously simplified versions of real neural networks that there might still be something to be learnt from the real brain. This shall not imply that to achieve intelligence, the solution necessarily has to mimic a biological brain.

(Thank you for your detailed response. I love to read about this stuff!)

edit: missing word

Re: Yann LeCun's comment on AlphaGo and true AI

#193

Post by scotty79 »

elementalest wrote: post #121
scotty79 wrote: post #117

> As I've said in previous statements: most of human and animal learning is unsupervised learning. I don't think that's true. When baby is learning to use muscles of its hands to wave them around there's no teacher to tell it what should its goal be. But physics and pain teaches it fairly efficiently which moves are bad idea. It has built in face detection engine and the orienting and attempting to move and reach tow…

The difference between supervised and unsupervised is that the inputs are paired with known outputs for supervised. In unsupervised the agent has (initially) no knowledge of what the outputs will be, given the inputs. The baby does not know (initially) that something will cause pain, or the extremities of its joints. It must learn this over time and experience. The baby must also learn how to use the built in compone…

> The difference between supervised and unsupervised is that the inputs are paired with known outputs for supervised. In unsupervised the agent has (initially) no knowledge of what the outputs will be, given the inputs.

I'd still call learning to move, supervised (or reinforced) then. You're feeding the world some input (muscle contractions), and the world immediately gives you the output in terms of pain. You are using it to adjust your internal function. After a while you have pretty good function that maps you muscle contractions to whether it valid move or not and you can generalize it to when your position is different and get to some other stuff like trying which moves can alter what you see and feel (apart from your hands that you already know).

> If there was no basic structure to the brain, I think it would be almost impossible for an unsupervised agent to develop and learn to the complexity and level of a human brain.

I agree that there's some stuff built in, but I think it's surprisingly little of it. How little I think we can see when we learn about people blind from birth or with deformities. They still learn to operate their bodies as well as it's physically possible.

Whatever person can relearn after physical brain damage I think can't be built-in. I think the structure we see in the brain is result of built-ins + various structural optimizations that make some stuff faster (or more energy efficient) than if the structure was different.

For me the real trick in neural networks is to find out how exactly natural neurons learn because it's not back-propagation and it's important. Do we know that? In detail? How scratching yourself on the face as a baby translates to chemical changes in synapses of neurons that fired recently?

Re: Yann LeCun's comment on AlphaGo and true AI

#194

Post by sampo »

Houshalter wrote: post #187
sampo wrote: post #72

Earlier quoted context omitted.

> We are still a ways away from AGI, but it's now in sight. These people in 1956 also thought that AGI was in sight: https://en.wikipedia.org/wiki/Dartmouth_Conferences

Not most of them, and not with any certainty. The Dartmouth conference was just the very first investigation into whether it was even possible and what it would take. Of course they didn't know when AGI would be developed. The computers they had access to were smaller than my calculator! Now we have massive computers and 60 years of progress. And lots of real world successes of AI technology. Surely we are in a much…

> Not most of them, and not with any certainty.

This probably holds true also today.

Re: Yann LeCun's comment on AlphaGo and true AI

#195

Post by sabertoothed »

nabla9 wrote: post #185
sabertoothed wrote: post #155

Earlier quoted context omitted.

I could not follow your argument. Could you elaborate? (Honest question)

Reinforcement learning is learning by interacting with an environment. RL agent learns from the consequences of its actions. Biological system don't live long enough to get enough feedback to learn complex behavior trough consequences. Animal or human must be able to generalize and categorize what they have learned correctly without external feedback teaching it how to derive the function that's doing it. For example…

Ok, I see what you mean now.

But it seems like (or one could misunderstand you in way that) you see those concepts as mutually exclusive. I would assume a combination of reinforcement learning and unsupervised (and supervised) learning.

Rats have been trained to detect landmines and then go back to their trainers and show them the mine. This is complex behaviour that was taught using reinforcement (at least on a top level). There will be some unsupervised learning going on in the rat's brain on a lower level. But it is complex behaviour and it's been reinforcement learnt.

Re: Yann LeCun's comment on AlphaGo and true AI

#196

Post by nabla9 »

sabertoothed wrote: post #195
nabla9 wrote: post #185

Earlier quoted context omitted.

Reinforcement learning is learning by interacting with an environment. RL agent learns from the consequences of its actions. Biological system don't live long enough to get enough feedback to learn complex behavior trough consequences. Animal or human must be able to generalize and categorize what they have learned correctly without external feedback teaching it how to derive the function that's doing it. For example…

Ok, I see what you mean now. But it seems like (or one could misunderstand you in way that) you see those concepts as mutually exclusive. I would assume a combination of reinforcement learning and unsupervised (and supervised) learning. Rats have been trained to detect landmines and then go back to their trainers and show them the mine. This is complex behaviour that was taught using reinforcement (at least on a top…

>see those concepts as mutually exclusive.

I certainly don't. Reinforcement or conditioning is part of it, but it's not the cake.

Re: Yann LeCun's comment on AlphaGo and true AI

#197

Post by GFK_of_xmaspast »

chrischen wrote: post #99
sytelus wrote: post #87

If you look at how child learns, it's huge amount of supervised learning. Parents spend lots of time in do and don't and giving specific instructions on everything from how to use toilet to how to construct a correct sentence. Lots of language development, object identification, pattern matching, comprehension, math skills, motor skills, developing logic - these activities has huge amount of supervised training that…

Err. A human is capable of unsupervised learning. Try locking two kids in a room for over decade. Maybe she didn't develop speech and social skills because there was no one to speak to or socialize with.

It's been done: https://en.wikipedia.org/wiki/Language_deprivation_experimen...

Re: Yann LeCun's comment on AlphaGo and true AI

#198

Post by zardo »

daveguy wrote: post #183
pavanky wrote: post #36

Can someone more knowledgeable explain why biological systems are considered unsupervised instead of reinforcement based systems? While it seems intuitive that most individual "intelligent" systems in animals can be seen as unsupervised, isn't life itself driven in a reinforced manner?

In AI the definition of reinforcement learning vs unsupervised is that reinforcement requires external identification of the correct result to compare with the given result. If going through life you had artificial reality display that flashed "apple" in front of every apple and "orange" in front of every orange you would have reinforcement learning. There is certainly a major component of reinforcement in teaching,…

You're describing supervised learning. Reinforcement learning is more like you stick random things in your mouth, and if one tastes good, you learn to stick that kind of thing in your mouth more often.

Re: Yann LeCun's comment on AlphaGo and true AI

#199

Post by zardo »

jacquesm wrote: post #140
doctorstupid wrote: post #131

Earlier quoted context omitted.

This is besides your main point, but I just want to add that the 'problem' of Go is not nearly solved. Rather, nearly solved is the problem of beating a human Go player. There is quite a difference.

> the 'problem' of Go is not nearly solved. And it is very likely that it will never be, the number of combinations is simply too large.

That doesn't (necessarily) mean a proof can't be found that a certain ruleset leads to optimal play. Tic-tac-toe can be solved without examing the entire state space of the game.

Re: Yann LeCun's comment on AlphaGo and true AI

#200

Post by daveguy »

zardo wrote: post #198
daveguy wrote: post #183

Earlier quoted context omitted.

In AI the definition of reinforcement learning vs unsupervised is that reinforcement requires external identification of the correct result to compare with the given result. If going through life you had artificial reality display that flashed "apple" in front of every apple and "orange" in front of every orange you would have reinforcement learning. There is certainly a major component of reinforcement in teaching,…

You're describing supervised learning. Reinforcement learning is more like you stick random things in your mouth, and if one tastes good, you learn to stick that kind of thing in your mouth more often.

Well, yes, I was describing supervised learning (as what doesn't happen) where labels are not present is unsupervised (which makes things much more difficult). Reinforcement is more like a special case between supervised and unsupervised. Difficult like unsupervised because the labels aren't known, but with some feedback that is not a direct answer. Sorry for the confusion. There is very little in the way of purely unsupervised learning. I think the distinction between unsupervised and reinforcement is not very well defined. I would argue that even a "pure" unsupervised algorithm like k-means has a kind of reinforcement in the group means.
Post reply on HN