> Human brains do this by deep double descent-style overparameterization, and adopting a scaling strategy of extremely high-learning-rate training of extremely overparameterized models on small diverse highly-filtered datasets.
That’s an extremely steep claim with no source other than vibes. Last time I checked my biology notes, model parameters are neurons, and they cost a ton of energy to maintain. Your hypothesis is really far removed from any actual neuroscience. Also, where are those filtered datasets coming from? Do you think genetics hands them to us? There’s about zero evidence for this claim as well.
I like new concepts for ML research but please do not make up theories of human cognition when you clearly have no idea about it.
We have a lot of synapses, but (agreeing with you) I don't find that sufficient to explain why humans (or animals!) do what we do. If you throw zillions of parameters at a problem with a weak architecture, you get really high-fidelity memorization, and we're not awesome at memorization compared to machines.
Humans can do an impressive amount of generalization from one error or surprise, and as is often rightly noted, don't need trillions of words to get going. And it all seems to happen some 'forward-only' way, without backpropagation -- we don't have AdamW or MuonClip helpfully nudging our synaptic connections towards whatever would have scored well on our most recent test. It is relevant that we're creatures with goals -- reinforcement learning is the only stage where there's a taste of that for neural nets -- but the learning differences seem at least partly independent of that.
I suppose it could turn out that, even if not sufficient, the large number of synapses is necessary to all this, like we're effectively buying a lot of lottery tickets that give us a shot at fishing interesting hypotheses out of the experiences flowing by. But I'm still awfully suspicious that we don't have the right mathematical model for learning messy ideas all worked out yet.
There is actually a way to get really amazing sample efficiency out of a learning setup, and that's engineering in a load of appropriate inductive biases, which personally I am convinced evolution has done for us. Explains a big chunk of the "how are brains so sample efficient" problem really easy, but unfortunately without handing us an easy way to replicate it, which makes it unpopular. Also, it's something that we don't really want to do in the same way evolution has, as all those biases do even further reduce sample efficiency for all the things for which they are not appropriate.
In a nutshell this is what statistical learning theory says. For any dataset there is an optimum given a prediction task. It follows from entropy. As the commenter pointed out “evolution has this backed in”. There once was a research direction of evolutionary distribution estimation algorithms but basically we know nothing about evolution, and scaling ede to multidimensional data is much harder than optimising objectives and trying to squeeze the inductive bias. For all it’s worth I think much of the current AI research is focused entirely on the wrong questions. Can machines learn? Sure, inductive bias FORCES them to learn. Given basically unlimited data can computers pick appropriate inductive biases to do anything useful, “survive” if you want to call it that… probably not, at least no one has really asked these questions for a couple of decades
- Human brains are estimated to have a few hundred trillion synapses. If you tried to replicate this in a neural network model with one parameter per synapse, it would be much larger than the largest models in use today.
- Conventional wisdom in form of the Chinchilla scaling law suggests that to train such a gargantuan model, you would need an even more gargantuan training corpus.
- But no human has read anywhere near as much as even relatively small Chinchilla-optimal models. In fact, rather than acquiring as much data as possible as efficiently as possible, children might rather rewatch the exact same video for the umpteenth time. When they learn arithmetic, it's from just a paltry few examples provided by the teacher in school.
- Large neural networks trained on such little training data would quickly memorize it perfectly and overfit horribly.
- Individuals with photographic memory demonstrate that human brains indeed have the memorization capacity you would expect based on synapse count, and appear to show difficulties with generalization as a side-effect.
- Speculatively, typical humans forget and generalize instead of memorizing because synaptic strengths are reduced during sleep in an analogue to regularization by weight decay.
- Therefore, maybe we should train extremely large models on little data with extremely strong weight decay to counteract memorization, and hope a large learning rate will quickly "catapult" it to a generalizing solution.
What I'm missing is a discussion of how much this would cost, even if you handle deployment by distillation into smaller, faster, less data-efficient models.
> Human brains are estimated to have a few hundred trillion synapses. If you tried to replicate this in a neural network model with one parameter per synapse...
Note that LLM parameters don't map to synapses in the same naive way they would for a fully connected network. Each attention parameter is applied thousands or millions of times to the inputs at each inference pass, so it's more like each param might code for a neural circuit repeated thousands of times.
I think of attention as a sort of convolution: in a NN, each convolution kernel gets applied repeatedly to all parts of an image, but in the human visual cortex I imagine these circuits are effectively all separate and parallel. The few parameters of a convolution kernel map to thousands of identical circuits in the visual cortex.
A biological synapse's weight takes effect whenever its input changes. So although it cannot be copied and applied in parallel to different inputs at the same time (and hence your visual cortex has a bunch of more-or-less identical edge-detection circuits) it can still be applied sequentially to different inputs at different times. And when LLMs do operate in sequential mode, generating tokens one at a time, they typically access each parameter at most once per forward pass.
Though there are things like looped transformers that reuse the same parameters multiple times even for a single token, so maybe those will finally give us AGI if scaled up to a trillion parameters and looped hundreds of times. (Sounds expensive!)
> A biological synapse's weight takes effect whenever its input changes.
I don't think it makes sense to try to compare our brains to ANN's, they are apples and oranges.
A synapse's weight is dynamically modulated by the astrocyte on multiple time scales (millisecond, sub-second, minutes), and the astrocyte itself is receiving inputs and performing computation (in addition to impacting the neural network).
>But no human has read anywhere near as much as even relatively small Chinchilla-optimal models
They're missing that humans don't consume raw text. They consume non-stop high resolution, high FPS audio and video imagery. If you tokenized the input to human eyes and ears in the first few years of life, that's more data than even the largest LLMs are trained on.
I didn't include it in my summary (it took me an hour to read the whole thing, obviously a lot had to be cut) but the article does actually address the "high resolution" argument in a three-paragraph bullet point under the "Sample Inefficiency" subheading: https://gwern.net/llm-catapult#sample-inefficiency If you read it on a 4K screen at 120 FPS, you should be able to take in its information content in less than a microsecond.
They "address" it by making false statement that the video stream is highly predictable. Sure, you might be able to predict 99% of video stream (for which you'd need to have a physics model, negating the whole point of baby fast learning), but the remaining 1% is still in terabytes if not petabytes per year.
And on the human side, disabled people are not much less intelligent than normal humans: deaf/blind people are much worse at language tasks, but their fluid intelligence often remains normal. If the sensory bandwidth were so critical, this would be impossible.
Human brains were trained by evolution, a genetic algorithm that ran for billions of years and used the entire planet Earth as compute. Good luck competing with it using your puny corpus of texts.
usernametaken29 | 16 hours ago
That’s an extremely steep claim with no source other than vibes. Last time I checked my biology notes, model parameters are neurons, and they cost a ton of energy to maintain. Your hypothesis is really far removed from any actual neuroscience. Also, where are those filtered datasets coming from? Do you think genetics hands them to us? There’s about zero evidence for this claim as well. I like new concepts for ML research but please do not make up theories of human cognition when you clearly have no idea about it.
jamwise | 16 hours ago
I guess at least they're honest about it? lol
twotwotwo | 14 hours ago
Humans can do an impressive amount of generalization from one error or surprise, and as is often rightly noted, don't need trillions of words to get going. And it all seems to happen some 'forward-only' way, without backpropagation -- we don't have AdamW or MuonClip helpfully nudging our synaptic connections towards whatever would have scored well on our most recent test. It is relevant that we're creatures with goals -- reinforcement learning is the only stage where there's a taste of that for neural nets -- but the learning differences seem at least partly independent of that.
I suppose it could turn out that, even if not sufficient, the large number of synapses is necessary to all this, like we're effectively buying a lot of lottery tickets that give us a shot at fishing interesting hypotheses out of the experiences flowing by. But I'm still awfully suspicious that we don't have the right mathematical model for learning messy ideas all worked out yet.
_0ffh | 13 hours ago
usernametaken29 | 8 hours ago
weregiraffe | 13 hours ago
yorwba | 13 hours ago
- Human brains are estimated to have a few hundred trillion synapses. If you tried to replicate this in a neural network model with one parameter per synapse, it would be much larger than the largest models in use today.
- Conventional wisdom in form of the Chinchilla scaling law suggests that to train such a gargantuan model, you would need an even more gargantuan training corpus.
- But no human has read anywhere near as much as even relatively small Chinchilla-optimal models. In fact, rather than acquiring as much data as possible as efficiently as possible, children might rather rewatch the exact same video for the umpteenth time. When they learn arithmetic, it's from just a paltry few examples provided by the teacher in school.
- Large neural networks trained on such little training data would quickly memorize it perfectly and overfit horribly.
- Individuals with photographic memory demonstrate that human brains indeed have the memorization capacity you would expect based on synapse count, and appear to show difficulties with generalization as a side-effect.
- Speculatively, typical humans forget and generalize instead of memorizing because synaptic strengths are reduced during sleep in an analogue to regularization by weight decay.
- Therefore, maybe we should train extremely large models on little data with extremely strong weight decay to counteract memorization, and hope a large learning rate will quickly "catapult" it to a generalizing solution.
What I'm missing is a discussion of how much this would cost, even if you handle deployment by distillation into smaller, faster, less data-efficient models.
throw310822 | 12 hours ago
Note that LLM parameters don't map to synapses in the same naive way they would for a fully connected network. Each attention parameter is applied thousands or millions of times to the inputs at each inference pass, so it's more like each param might code for a neural circuit repeated thousands of times.
I think of attention as a sort of convolution: in a NN, each convolution kernel gets applied repeatedly to all parts of an image, but in the human visual cortex I imagine these circuits are effectively all separate and parallel. The few parameters of a convolution kernel map to thousands of identical circuits in the visual cortex.
yorwba | 12 hours ago
Though there are things like looped transformers that reuse the same parameters multiple times even for a single token, so maybe those will finally give us AGI if scaled up to a trillion parameters and looped hundreds of times. (Sounds expensive!)
RaftPeople | 4 hours ago
I don't think it makes sense to try to compare our brains to ANN's, they are apples and oranges.
A synapse's weight is dynamically modulated by the astrocyte on multiple time scales (millisecond, sub-second, minutes), and the astrocyte itself is receiving inputs and performing computation (in addition to impacting the neural network).
logicchains | 12 hours ago
They're missing that humans don't consume raw text. They consume non-stop high resolution, high FPS audio and video imagery. If you tokenized the input to human eyes and ears in the first few years of life, that's more data than even the largest LLMs are trained on.
yorwba | 11 hours ago
lostmsu | 10 hours ago
nnoremap | 8 hours ago
weregiraffe | 12 hours ago