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

TopoNets: High performing vision and language models with brain-like topography

arxiv.org

Post reply on HN
Print view View original

41–50 of 76 posts

Re: TopoNets: High performing vision and language models with brain-like topography

#41

Post by dmarchand90 »

gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

I've found how CNN map to visual cortex to be very clear. But I've always been a bit confused about how llms map to the brain. Is that even the case?

Re: TopoNets: High performing vision and language models with brain-like topography

#42

Post by immibis »

mayukhdeb wrote: post #27
cwillu wrote: post #23

Earlier quoted context omitted.

Was it toxicity though as understood by the model, or just a cluster of concepts that you've chosen to label as toxic? I.e., is this something that could (and therefore, will) be turned towards identifying toxic concepts as understood by the chinese or us government, or to identify (say) pro-union concepts so they can be down-weighted in a released model, etc?

We localized "toxic" neurons by contrasting the activations of each neuron for toxic v/s normal texts. It's a method inspired by old-school neuroscience.

Defining all politics as toxic is concerning, if it's not just a proof of concept. That's something dictatorships do so that people won't speak up.

Re: TopoNets: High performing vision and language models with brain-like topography

#43

Post by trhway »

lukan wrote: post #40
gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

"It’s amazing how closely this synthetic perceptual pipeline parallels the way our own brains interpret the world." It is amazing, that the synthetic pipeline, that was build to mimick the brain, seems to mimick the brain? That sounds a bit tautological and otherwise I doubt we have really understood how our brain exactly interprets the world. In general this is definitely interesting research, but worded like this,…

The convolutional kernels in the first levels do converge to Gabors like the ones in V1 (and there were math works in the 90-ies, in neuro research, about optimality of such kernels) so it wouldn't be surprising if higher levels would converge to something that is similar to the higher levels of visual cortex (like hierarchical feature aggregation that is nicely illustrated by deep dreaming and also feels like it can be optimal under reasonable conditions and thus would be expected to emerge).

Re: TopoNets: High performing vision and language models with brain-like topography

#44

Post by trhway »

dmarchand90 wrote: post #41
gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

I've found how CNN map to visual cortex to be very clear. But I've always been a bit confused about how llms map to the brain. Is that even the case?

> how llms map to the brain

For the lower level - word embedings (word2vec, "King – Man + Woman = Queen") - one can see a similarity

https://www.nature.com/articles/d41586-019-00069-1 and https://gallantlab.org/viewer-huth-2016/

"The map reveals how language is spread throughout the cortex and across both hemispheres, showing groups of words clustered together by meaning."

Re: TopoNets: High performing vision and language models with brain-like topography

#45

Post by w-m »

ziofill wrote: post #19
energy123 wrote: post #5

The main reason topography emerges in physical brains is because spatially distant connections are physically difficult and expensive in biological systems. Artificial neural nets have no such trade-off. So what's the motivation here? I can understand this might be a very good regularizer, so it could help with generalization error on small-data tasks. But hard to see why this should be on the critical path to AGI. A…

Perhaps they are more easily compressible? Once a bunch of nearby weights have similar roles one may not need all of them.

If you have things organized neatly together, you can also use pre-existing compression algorithms, like JPEG, to compress your data. That's what we're doing in Self-Organizing Gaussians [0]. There we take an unorganised (noisy) set of primitives that have 59 attributes and sort them into 59 2D grids which are locally smooth. Then we use off-the-shelf image formats to store the attributes. It's an incredibly effective compression scheme, and quite simple.

[0]: https://fraunhoferhhi.github.io/Self-Organizing-Gaussians/

Re: TopoNets: High performing vision and language models with brain-like topography

#46

Post by iandanforth »

gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

Unlike neural networks the brain contains massive numbers of lateral connections. This, combined with topographical organization, allows it to do within layer temporal predictions as activations travel across the visual field, create active competition between similarly tuned neurons in a layer (forming natural sub networks), and quite a bit more. So, yeah, the brain's organisation serves it's function, and it does so very very well.

Re: TopoNets: High performing vision and language models with brain-like topography

#47

Post by perching_aix »

lukan wrote: post #40
gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

"It’s amazing how closely this synthetic perceptual pipeline parallels the way our own brains interpret the world." It is amazing, that the synthetic pipeline, that was build to mimick the brain, seems to mimick the brain? That sounds a bit tautological and otherwise I doubt we have really understood how our brain exactly interprets the world. In general this is definitely interesting research, but worded like this,…

Did you read the part where he explicitly mentioned that they discovered how enforcing that architecture was not necessary, as it would emerge on its own?

Re: TopoNets: High performing vision and language models with brain-like topography

#48

Post by lukan »

perching_aix wrote: post #47
lukan wrote: post #40

Earlier quoted context omitted.

"It’s amazing how closely this synthetic perceptual pipeline parallels the way our own brains interpret the world." It is amazing, that the synthetic pipeline, that was build to mimick the brain, seems to mimick the brain? That sounds a bit tautological and otherwise I doubt we have really understood how our brain exactly interprets the world. In general this is definitely interesting research, but worded like this,…

Did you read the part where he explicitly mentioned that they discovered how enforcing that architecture was not necessary, as it would emerge on its own?

I did, but it was not clear to me, how it was meant. I assume the basic design was done before (with the brain in mind).

Re: TopoNets: High performing vision and language models with brain-like topography

#49

Post by Shorel »

lukan wrote: post #40
gzer0 wrote: post #39

I spent time working with Andrej and the rest of the FSD team back in 2020/2021, and we had plenty of conversations on how human visual processing maps onto our neural network architectures. Our approach—transformer-based attention blocks, multi-scale feature extraction, and temporal fusion—mirrors elements of the biological visual cortex (retina → LGN → V1 → V2 → V4 → IT) which break down raw inputs and integrate th…

"It’s amazing how closely this synthetic perceptual pipeline parallels the way our own brains interpret the world." It is amazing, that the synthetic pipeline, that was build to mimick the brain, seems to mimick the brain? That sounds a bit tautological and otherwise I doubt we have really understood how our brain exactly interprets the world. In general this is definitely interesting research, but worded like this,…

I interpreted it the other way around.

We can think of a solution space, with potentially many good solutions to the vision problem, and we can, in science fiction-like speculation, that the other solutions will be very different and surprise us.

Then this experiment shows its solution is the same we already knew, and that's it.

Then there aren't many good potential solutions, there is only one, and the ocean of possibilities becomes the pond of this solution.

Re: TopoNets: High performing vision and language models with brain-like topography

#50

Post by brrrrrm »

FrereKhan wrote: post #30

This paper imports an arbitrarily-chosen aspect of cortical architecture — topological maps of function — and ignores every other aspect of biological neural tissue. The resulting models show lower performance for the same number of parameters — not surprising, since they are more constrained compared with baseline. They may be slightly more robust against pruning — not surprising, since they are more regularised. Th…

this paper plays into some popular fantasy about the aesthetic of ANNs. it’s not scientifically useful
Post reply on HN