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

Study urges caution when comparing neural networks to the brain

news.mit.edu

Post reply on HN
Print view View original

81–90 of 141 posts

Re: Study urges caution when comparing neural networks to the brain

#81

Post by tabtab »

marginalia_nu wrote: post #71
lalos wrote: post #28

Here's my guess: neurons tap into quantum mechanics but we are too primitive to understand that for now. The brain was initially modeled as humors/fluids back when we developed aqueducts, then telegraph came into the scene and it was modeled as electrical impulses and now computers/ML are popular therefore we see it as a neural network. Next step is quantum.

Neurons almost certainly use quantum processes, but so do most transistors. The brain is too too warm for large-scale quantum effects though. You're not going to find phase coherence at that scale in such an environment, which is pretty much the prerequisite for quantum effects (that is fairly well understood).

I believe what was meant was quantum-only or primarily-quantum effects rather than the aggregate effects we normally see (classic physics & chemistry), which are probably the result of quantum physics, but we have "classic" abstractions that model them well enough. Thus, the issue is whether the brain relies mostly on classic effects (common aggregate abstractions) for computations or on quantum-specific effects.

Re: Study urges caution when comparing neural networks to the brain

#82

Post by GuB-42 »

retrac wrote: post #69
lalos wrote: post #28

Here's my guess: neurons tap into quantum mechanics but we are too primitive to understand that for now. The brain was initially modeled as humors/fluids back when we developed aqueducts, then telegraph came into the scene and it was modeled as electrical impulses and now computers/ML are popular therefore we see it as a neural network. Next step is quantum.

It's certainly not proven, but there are many hints in that direction, and the hints keep piling up. Recent research [1] on how the classic anaesthetics work (a great mystery!) suggests they operate by inhibiting the entanglement of pairs of electrons in small molecules which split into free radicals, the electrons then physically separated but still-entangled. It seems it is at least possible, that there is speed-of…

Isn't it just chemistry?

Chemistry is quantum physics at its core. It is just that quantum equations are so hard to solve for anything bigger than hydrogen that most of the times, chemists prefer to use empirical rules to do their job.

Re: Study urges caution when comparing neural networks to the brain

#83

Post by ouid »

ffwd wrote: post #67
bawolff wrote: post #38

The aspect of ai that makes me think something related is going on, is how artifacts look in image generation systems like stable diffusion. Often these systems will have really bizzare artificats, people with 3 arms, etc. However at the same time when you glance at the output without looking carefully you will sometimes miss these artifacts even though they should be absolutely glaring.

Not sure if I'm missing a subtle nuance in your point but to me those "artifacts" are completely expected. Those artifacts like 3 arms are the patterns / outputs in the model, but since it doesn't have a fundamental understanding of the patterns/objects like arms, it just blends many images of arms together and create things like 3 arms. Also why there are so many eyes, arms, legs and other things in other generative…

the hierarchical structure of the visual system is a completely emergent property of the fact that the visual brain is a three dimensional object encoding a 2 dimensional objecr efficiently by maintaining the spatial relation present in the data in the representation until you have finished using it.

There's simply nowhere for the computation to go.

Re: Study urges caution when comparing neural networks to the brain

#84

Post by marginalia_nu »

tabtab wrote: post #81
marginalia_nu wrote: post #71

Earlier quoted context omitted.

Neurons almost certainly use quantum processes, but so do most transistors. The brain is too too warm for large-scale quantum effects though. You're not going to find phase coherence at that scale in such an environment, which is pretty much the prerequisite for quantum effects (that is fairly well understood).

I believe what was meant was quantum-only or primarily-quantum effects rather than the aggregate effects we normally see (classic physics & chemistry), which are probably the result of quantum physics, but we have "classic" abstractions that model them well enough. Thus, the issue is whether the brain relies mostly on classic effects (common aggregate abstractions) for computations or on quantum-specific effects.

I don't think that's a meaningful distinction. Many effects in classical physics are just previously poorly understood quantum effects. The distinction has more to do with when they were discovered than what causes them. Electricity is a good example. A large reason why electrons act collectively the way they do is a direct consequence of the pauli exclusion principle.

Re: Study urges caution when comparing neural networks to the brain

#85

Post by cma »

ffwd wrote: post #67
bawolff wrote: post #38

The aspect of ai that makes me think something related is going on, is how artifacts look in image generation systems like stable diffusion. Often these systems will have really bizzare artificats, people with 3 arms, etc. However at the same time when you glance at the output without looking carefully you will sometimes miss these artifacts even though they should be absolutely glaring.

Not sure if I'm missing a subtle nuance in your point but to me those "artifacts" are completely expected. Those artifacts like 3 arms are the patterns / outputs in the model, but since it doesn't have a fundamental understanding of the patterns/objects like arms, it just blends many images of arms together and create things like 3 arms. Also why there are so many eyes, arms, legs and other things in other generative…

> but since it doesn't have a fundamental understanding of the patterns/objects like arms, it just blends many images of arms together and create things like 3 arms.

But it rarely would put out say 8 arms. And the repeat artifacts are miles ahead of earlier stuff like clip draw or disco diffusion. So it does seem to have some idea of what's going on, just isn't perfect yet. It gets much worse without the 512x512 resolution, if you push both dimensions it loses scene coherence a lot more.

Re: Study urges caution when comparing neural networks to the brain

#86

Post by ffwd »

l33tman wrote: post #77
ffwd wrote: post #67

Earlier quoted context omitted.

Not sure if I'm missing a subtle nuance in your point but to me those "artifacts" are completely expected. Those artifacts like 3 arms are the patterns / outputs in the model, but since it doesn't have a fundamental understanding of the patterns/objects like arms, it just blends many images of arms together and create things like 3 arms. Also why there are so many eyes, arms, legs and other things in other generative…

"It just spits out the training set in random configurations (ish)." is a pretty gross misrepresentation and oversimplification of how such a model works, akin to saying a human artist only spits out whatever they saw earlier in their life in random configurations, or saying that SD only spits out pixel values it has seen before, or combinations of pixel values that form edges, etc. FWIW I don't think there is anythi…

I get your point, but I also think it depends on what you mean by oversimplification. Of course there is _a lot_ of stuff going on and things like SD capture all kinds of information, not just what I described, however, any way you want to describe it, capturing all the "constraints" and real life knowledge to perfectly create realistic images with all the details and all the higher abstractions correctly is not anywhere close I think. Also it's not only to always get 2 arms, it's to - at the same time - also get 2 ears, 2 eyes, perfect pupils, perfect fingers, perfect trees, perfect chairs, all simultaneously (if it is to be used at least in the mainstream) - etc you get my point.

I also don't think there's anything wrong with the model architectures in themselves or the data, nor that it is impossible, only that it is hard and as you say I think it needs a lot of data and clever engineering to fix mistakes. It may even be possible to fix most mistakes, over time, which would be pretty impressive imo, but the absolute limits of what a model can produce/"contain" with our hardware is kind of an open question though interesting.

Re: Study urges caution when comparing neural networks to the brain

#87

Post by tobyjsullivan »

> Study urges caution when comparing neural networks to the brain

They keep telling me this and, yet, I can't stop doing it. The more I learn about neural networks, the more I feel like I understand my own brain (whether accurate or not). And conversely, the more I think about thinking, the better my theories about how I'd build ML-based system to solve specific problems (admittedly, most untested). Neural networks seem like too useful of a model to simply give up because they aren't completely accurate.

Of course, this is all just for personal use - mostly introspection. I wouldn't exactly do medical work based on the model.

Re: Study urges caution when comparing neural networks to the brain

#88

Post by colechristensen »

tobyjsullivan wrote: post #87

> Study urges caution when comparing neural networks to the brain They keep telling me this and, yet, I can't stop doing it. The more I learn about neural networks, the more I feel like I understand my own brain (whether accurate or not). And conversely, the more I think about thinking, the better my theories about how I'd build ML-based system to solve specific problems (admittedly, most untested). Neural networks s…

People always do things like this, like an astrologer trying to say something profound using Heisenberg's uncertainty principle applying it to your romantic relationships, or whatever.

These "just so" stories are attractive but it is quite important to realize a metaphor which is intuitive and you perceive as useful is nothing at all like the process for finding real scientific truth. There is also a lot of introspective value to modeling the world as being controlled by mysterious gods who are pleased or appalled at your behavior and that's why good and bad things happen. Perhaps useful for some people but nothing at all like truth.

https://en.wikipedia.org/wiki/Just-so_story

Re: Study urges caution when comparing neural networks to the brain

#89

Post by dekhn »

russdill wrote: post #70
dekhn wrote: post #50

Earlier quoted context omitted.

I think you're probably missing a number of the important details. In the Penrose/Hammerof model, they're explicitly saying that humans are observed to generate problem solutions that could not have been generated by a purely classical computing process, therefore, the brain must exploit some specific quantum phenomenon. When you talk about QM a a theory of how the world operates, there are wide ranges of QM. Everyth…

The set of problems that are computable by a classical computer are the same set of problems computable by a quantum computer. I think you might be misstating the Penrose argument/position.

I'm fairly certain I'm giving a passable description of what Penrose claims in https://en.wikipedia.org/wiki/The_Emperor%27s_New_Mind and and https://en.wikipedia.org/wiki/Shadows_of_the_Mind

I should have said "problems which do not have computable solutions" rather than "set of problems computable by a quantum computer", which seems fairly pedestrian compared to what Penrose is saying.

Re: Study urges caution when comparing neural networks to the brain

#90

Post by colechristensen »

cuteboy19 wrote: post #64
ben_w wrote: post #41

Earlier quoted context omitted.

22 May 2018: https://arxiv.org/abs/1802.08195

I wonder if adversarial attacks can be mitigated by simply passing a few transforms of the same image to the neural network.

This is often a big part of how neural networks are trained. Take labelled photos (really it applies in abstract ways to other data) add a little noise, mirror, shrink and stretch, translate to a different area, etc. One piece of data becomes several training images.

And no, this standard practice does not eliminate adversaries.

Post reply on HN