Brain learns through pain. LLMs learn through expending energy.
Inferring neural activity before plasticity for learning beyond backpropagation
41–50 of 50 posts
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#42It has been clear for a long time (e.g. Marvin Minsky's early research) that: 1. both ANNs and the brain need to solve the credit assignment problem 2. backprop works well for ANNs but probably isn't how the problem is solved in the brain This paper is really interesting, but is more a novel theory about how the brain solves the credit assignment problem. The HN title makes it sound like differences between the brain…
Are there any results about the "optimality" of backpropagation? Can one show that it emerges naturally from some Bayesian optimality criterion or a dynamic programming principle? This is a significant advantage that the "free energy principle" people have. For example, let's say instead of gradient descent you want to do a Newton descent. Then maybe there's a better way to compute the needed weight updates besides b…
I'd be willing to be proven wrong, but as a starting point I'd suggest it obviously isn't optimal for what it is being used for. The performance on tasks of AI seems to be quite poor relative to the time spent training. For example, when AIs overtake humans at Baduk it is normal for the AI to have played several orders of magnitude more games than elite human players.
The important thing is backprop does work and so we're just scaling it up to absurd levels to get good results. There is going to be a big step change found sooner or later where training gets a lot better. Maybe there is some sort of threshold we're looking for where a trick only works for models with lots of parameters or something before we stumble on it, but if evolution can do it so will researchers.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#43It has been clear for a long time (e.g. Marvin Minsky's early research) that: 1. both ANNs and the brain need to solve the credit assignment problem 2. backprop works well for ANNs but probably isn't how the problem is solved in the brain This paper is really interesting, but is more a novel theory about how the brain solves the credit assignment problem. The HN title makes it sound like differences between the brain…
> The HN title makes it sound like differences between the brain and ANNs were previously unknown and is misleading IMO There are no words in the title which express this. Your own brain is "making it sound" like that. Misleading, yes, but attribute it correctly.
The title does express that, due to context. An article in Nature with the title "X is Y" suggests that, until now, we didn't know that X is Y, or we even thought that X is definitely not Y.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#44Some are surprised that anyone would make this point, either the title or the research. It might be a response to the many, many claims in articles that neural networks work like the brain. Even using terms like neurons and synapses. With those claims getting widespread, people also start building theories on top of them that make AI’s more like humans. Then, we won’t need humans or they’ll be extinct or something. M…
> Even using terms like neurons and synapses. With those claims getting widespread, people also start building theories on top of them that make AI’s more like humans. Except the networks studied here for prospective configuration are ... neural networks. No changes to the architecture have been proposed, only a new learning algorithm. If anything, this article lends credence to the idea that ANNs do -- at some level…
"Except the networks studied here for prospective configuration are ... neural networks. No changes to the architecture have been proposed, only a new learning algorithm."
In scientific investigations, it's best to look at one component, or feature, at a time. It's also common to put the feature in an existing architecture to assess the difference that feature makes in isolation. Many papers trying to imitate brain architecture only use one feature in the study. I've seen them try stateful neurons, spiking, sparsity, Hebbian learning, hippocampus-like memory, etc. Others will study combinations of such things.
So, the field looks at brain-inspired changes to common ML, specific components that closely follow brain design (software or hardware), and whole architectures imitating brain principles with artificial deviations. And everything in between. :)
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#45It has been clear for a long time (e.g. Marvin Minsky's early research) that: 1. both ANNs and the brain need to solve the credit assignment problem 2. backprop works well for ANNs but probably isn't how the problem is solved in the brain This paper is really interesting, but is more a novel theory about how the brain solves the credit assignment problem. The HN title makes it sound like differences between the brain…
> The HN title makes it sound like differences between the brain and ANNs were previously unknown and is misleading IMO. Agreed on both counts. There's nothing surprising in "there are differences between the brain and ANN's." But their might be something useful in the "novel theory about how the brain solves the credit assignment problem" presented in the paper. At least for me, it caught my attention enough to just…
s/their might/there might/
Dang it, how did I miss that. Uugh. :-(
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#46Earlier quoted context omitted.
> It might be a response to the many, many claims in articles that neural networks work like the brain. Even using terms like neurons and synapses. Artificial neural networks originated as simplified models of how the brain actually works. So they really do "work like the brain" in the sense of taking inspiration from certain rudiments of its workings. The problem is "like" can mean anything from "almost the same as"…
Brain-inspired, neuromorphic architectures are usually very different from neural networks in machine learning. They’re so different (and better) that people who know both keep trying to reproduce brain-like architecture to gain its benefits. One of my favorite features is how they use local, likely Hebbian, learning instead of global with backpropagation. (I won’t rule out some global mechanism, though.) The local l…
Totally agree! The "fire together, wire together" approach to training weights is super easy to parallelize, and you can design custom silicon to make it ridiculously efficient. Back when I was a Computational Neuroscience (CN) researcher, I worked with a team in Manchester that was exploring exactly that—not sure if they ever nailed it...
Funny enough, I actually worked with Rafal Bogacz, the last-named author of the paper we’re discussing, during his Basal Ganglia (BG) phase. He’s an incredibly sharp guy and made a pretty compelling argument that the BG implement the multihypothesis sequential probability ratio test (MSPRT) to decide between competing action plans in an optimal way.
Back then, there was another popular theory that the BG used an actor-critic learning model—also quite convincing.
But here’s the rub: in CN, the trend is to take algorithms from computer science and statistics and map them onto biology. What’s far rarer is extracting new ML algorithms from the biology itself.
I got into CN because I thought the only way we’d ever crack AGI was by unlocking the secrets of the best example we’ve got—the mammalian brain. Unfortunately, I ended up frustrated with the biology-led approach. In ten years in the field, I didn’t see anything that really felt like progress toward AGI. CN just moves so much slower than mainstream ML!
Still, I hope Rafal’s onto something with this latest idea. Fingers crossed it gives ML researchers a shiny new algorithm to play with.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#47Earlier quoted context omitted.
> Even using terms like neurons and synapses. With those claims getting widespread, people also start building theories on top of them that make AI’s more like humans. Except the networks studied here for prospective configuration are ... neural networks. No changes to the architecture have been proposed, only a new learning algorithm. If anything, this article lends credence to the idea that ANNs do -- at some level…
"Except the networks studied here for prospective configuration are ... neural networks. No changes to the architecture have been proposed, only a new learning algorithm." In scientific investigations, it's best to look at one component, or feature, at a time. It's also common to put the feature in an existing architecture to assess the difference that feature makes in isolation. Many papers trying to imitate brain a…
I'm not sure what you're trying to say here. Hebbian learning is the basis for current ANNs. Spiking neural nets again an adaptation of neural nets. The entire field is inspired by nature and has been an a never ending quest to replicate it
This paper is an incremental step along that path but commenters here are acting as if it's a polemic against neural nets.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#48It has been clear for a long time (e.g. Marvin Minsky's early research) that: 1. both ANNs and the brain need to solve the credit assignment problem 2. backprop works well for ANNs but probably isn't how the problem is solved in the brain This paper is really interesting, but is more a novel theory about how the brain solves the credit assignment problem. The HN title makes it sound like differences between the brain…
Are there any results about the "optimality" of backpropagation? Can one show that it emerges naturally from some Bayesian optimality criterion or a dynamic programming principle? This is a significant advantage that the "free energy principle" people have. For example, let's say instead of gradient descent you want to do a Newton descent. Then maybe there's a better way to compute the needed weight updates besides b…
> For example, let's say instead of gradient descent you want to do a Newton descent. Then maybe there's a better way to compute the needed weight updates besides backprop?
IIRC, feedback alignment [1] approximates Gauss-Newton minimization. So there is an easier way, that is potentially biologically more plausible, though not necessarily a better way.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#49"AI and Human learn differently."
Obviously. So can the scraping grifters who claim that AI 'learns just like a human' please shut up and never inflict their odious presence on the rest of humanity again? And also pay 10X damages for ruining the Internet.
Re: Inferring neural activity before plasticity for learning beyond backpropagation
#50Wait, my brain doesn't do backprop over a pile of linear algebra after having the internet rammed through it? No way that's crazy /s tl;dr: paper proposes a principle called 'prospective configuration' to explain how the brain does credit assignment and learns, as opposed to backprop. Backprop can lead to 'catastrophic interference' where learning new things abalates old associations, which doesn't match observed bio…
This is like expressing surprise that a photon doesn't perform relativistic calculations on its mini chalkboard. A simulation of a thing is not thing itself, but it is illuminating. > pile of linear algebra The entirety of physics is -- as you say -- a 'pile of linear algebra' and 'backprop' (differential linear algebra...)
I don’t think “differential linear algebra” really counts as “backprop”.