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

131–140 of 141 posts

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

#131

Post by ben_w »

Jensson wrote: post #128
ben_w wrote: post #126

Earlier quoted context omitted.

We're not always aware of optical illusions. Not even dynamic ones. Magicians will tell you they're fooling you, but con artists can use many of the same patterns and you only find out too late.

Con artists isn't a big problem, if it worked on everyone then you would have con artists become the richest persons in the world. Like, just con Elon Musk out of his billions, why hasn't anyone done that yet if it is so easy to trick humans?

> Like, just con Elon Musk out of his billions, why hasn't anyone done that yet if it is so easy to trick humans?

Like getting him to spend $44 billion for Twitter?

(An ex of mine is convinced that Musk is a con artist, but she's also a literal card carrying anarcho-communist; I'm not that cynical about Musk).

Even at a lower level, I had my bank[0] call up and tell me there was too much money in my account and they'd really recommend a wealth management consultation to avoid me being scammed, and that wasn't even £100k.

That said, I was thinking mainly of street cons — shell games, possibly even shoplifting and pickpocketing — as the previous discussion was about optical illusions. Business level scams are about a broader category of cognitive bias, and I'd say almost all gambling is that type of thing, likewise bitcoin, dulce et decorum est, and populist politics.

[0] or at least they said they were, but I said no before getting to the point where asking for proof the call wasn't itself a scam would've been useful

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

#132

Post by bawolff »

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…

For me the distinction is that when an artist draws a 3 armed person it stands out immediately. This makes me feel like something is going on in the ai that is similar to our brains because the blindspots seem similar.

And you're right that this is pretty unfounded intuition. Humans often seek meaning in things without meaning, so it might be unfounded. At some point all i can really do is shrug and say it feels "spooky" to me.

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

#133

Post by ben_w »

elcomet wrote: post #127
ben_w wrote: post #76

Earlier quoted context omitted.

That's literally what I was saying when I wrote "our biases are how evolution managed to do that".

Yeah but I disagreed about your point "Current AI requires far more examples than we do to learn from", since I think you need to count the amount of data that was seen by all your ancesters, maybe even starting from the first self-replicating molecule, billion years ago.

Fair enough. I wouldn't go quite that far — at absolute most I would accept since the first prototype of a neural cell — but the estimates I've seen for what data/training AGI would need if it requires a simulated re-run of modern human evolution to be trained is more than current (or at least recent) AI.

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

#134

Post by wruza »

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…

Isn’t this because a training set usually consists 99% of implied things? Afaik, these never provide a full description like “…, also two hands, two legs, three fingers, arms not bent, adequately long limbs, leg asymmetry, cartoon physics, …”, and also never feed examples of a wrong geometry/biology/etc.

I’m no NN guy, but to me all it seems as basically underconstrained and unrelated to “understanding”. It’s like these e.g. woodwork, magic trick, dancing, guitar, etc teachers who fail to message a way to do something and can only tell “look”, then just do it, ask you to repeat, and get annoyed when you fail again.

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

#135

Post by 19h »

nl wrote: post #130
19h wrote: post #120

We've been doing significant research using HTM[1][2][3][4] w/ SDR[5] similar to the proprietary implementation of Semantic Folding[6] and were able to classify literally gigabytes of documents per second on FPGAs. HTM aims to resemble the architecture of the Neocortex. I simply don't understand why literally everyone immediately jumps at CNNs, RNNs (transformers et al.) -- they're extremely expensive, slow and defin…

> I simply don't understand why literally everyone immediately jumps at CNNs, RNNs (transformers et al.) -- they're extremely expensive, slow Because for text they work a lot better. HTMs are competitive with other non-NN techniques on small datasets (see [1] you listed) but nothing particularly amazing. I'd speculate this is because they use bag-of-word variants like LSI and TF-IDF. Prior to Transformers this was a…

We have seen significantly higher accuracy than that, more than competitive with the transformer approach we’ve been running in parallel. For arbitrary texts we’ve seen accuracies of at least 92%.

> If SIGINT in this context means signal intelligence (on text data) then I assure you that they are being used.

Maybe, I don’t know what projects you’ve been involved with. For the terabit-level pre-sorting of SIGINT data they’re absolutely definitely not used. If at all on the selected information of interest. My information concerns intel actors in Europe.

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

#136

Post by ffwd »

nullc wrote: post #111
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 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 programs. It just spits out the training set in random configurations" That is thoroughly confused to the point of uselessness. The reason you get structural issues is because it's hard for the architecture to express large scale structure, but they get better an…

It was poorly communicated in my post but what I was referring to there were earlier programs like in 2015 and not SD and newer ones. If you put in an image of a landscape it could fill out the landscape with eyes and elbows all over the generated image because it had no information or context for what an eye was or where it should go.

But now you get SD, dalle and others which add more information not just by scaling, but also by mapping sentences/words to pre-existing images that already have cohesion. That way when you write in sentences to the text prompt, the model has more semantic information about what an eye is, but (IMO) only _indirectly_ because it will map a sentence to images that match that sentence. The question is always what information is actually contained in the training set and what is missing from it and when it creates an image where is the information from etc.

In some ways, that means I think that meaning to us as humans, is different from scaling which is almost like pixel resolution except resolution of patterns and differentiation of patterns. Meaning in this sense is things like creating a doorway with no actual door, but still the doorway itself looks super realistic is rendered. You can fix it by scaling and increasing the differentiation of patterns I guess, but you can never fix all instances completely with scaling. That's why in some ways I think meaning is sort of orthogonal to scale, however on a philosophical level, they should converge but that's for another topic.

I may have missed something in my thoughts here because this is sort of difficult to talk about without writing a book eventually.

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

#137

Post by isaacfrond »

danielheath wrote: post #116
theptip wrote: post #100

> Networks trained on a path integration task almost always learn to optimally encode position, but almost never learn lattice cells (hexagonal or square) to do so... Our main message is that it is highly improbable that DL models of path integration would have produced grid cells as a novel prediction simply from task-training, had grid cells not already been known to exist. This carries on into an extremely nuanced…

In wet-brains: Interlacing isn't 4-way or 6-way, it's 10e3-way, and each interlaced connection has a weight that's nonlinearly time-dependant based on how long since last firing. Every cyclic connection is potentially a self-sustaining oscillator. None of these features are efficiently implemented in current silicon. "Caution when comparing neural networks to brains" is underselling it. They're profoundly different k…

What do you mean? Any image classifier will use way more than 4 kernels for convolution. All those layers are interlaced. Furthermore they also contain fully connected layers, with neuron integrating way more than 10^3 signals.

The reasons that there aren't much more fully connected layers, is that this doesn't work. Actually, one of the key developments in NNs is architectural, minpools, ReLus, U-net. All are key for modern networks, all architectural.

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

#139

Post by tabtab »

marginalia_nu wrote: post #84
tabtab wrote: post #81

Earlier quoted context omitted.

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: The distinction has more to do with when they were discovered than what causes them.

Well, okay. But so far there's no evidence to suggest the brain uses quantum effects discovered/verified fairly recently.

The "common" properties of electricity and chemistry where fairly well known and modelled well by 1900.

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

#140

Post by grantcas »

merely-unlikely wrote: post #66
RosanaAnaDana wrote: post #43

Earlier quoted context omitted.

I think anyone who has tripped would also commiserate. Seeing too many eyes or fingers at a glance. Things feeling cartoony or 'shiny'. I don't know if AGI is down the road diffusion models have taken us. I'm not even really sure what most people mean by AI when they talk about it. But stable diffusion et al are clearly super human. I'm not sure that AGI is down the trail cut by diffusion models, but if it's ever acc…

My pet (uneducated) theory is that AI needs to have a parent layer "consciousness" before it can become an AGI. Think of that voice inside your head and your ability to control bodily functions without needing to do it all the time. My model is our brains have many specialized "sub AIs" operating all the time (remembering to breathe for example) but then the AI behind the voice can come in and give commands that over…

[dead]
Post reply on HN