It 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 and ANNs were previously unknown and is misleading IMO.
> 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 justify giving it a full reading sometime soon.
> In prospective configuration, before synaptic weights are modified, neural activity changes across the network so that output neurons better predict the target output; only then are the synaptic weights (hereafter termed ‘weights’) modified to consolidate this change in neural activity. By contrast, in backpropagation, the order is reversed; weight modification takes the lead, and the change in neural activity is the result that follows.
What would neural activity changes look like in an ML model?
Theories that brains predict the pattern of expected neural activity aren't new, (eg this paper cites work towards the Free Energy Principle, but not Embodied Predictive Interoception Coding works). I have 0 neuroscience training so I doubt I'd be able to reliably answer my question just by reading this paper, but does anyone know how specifically their Prospective Configuration model differs, or expands, upon the previous work? Is it a better model of how brains actually handle credit assign than the aforementioned models?
The FEP is more about what objective function the brain (really the isocortex) ought to optimize. EPIC is a somewhat related hypothesis about how viscerosensory data is translated into percepts.
Prospective Configuration is an actual algorithm that, to my understanding, attempts to reproduce input patterns but can also engage in supervised learning.
I'm less clear on Prospective Configuration than the other two, which I've worked with directly.
The post headline is distracting people and making a poor discussion. The paper describes a learning mechanism that had advantages over backprop, and may be closer to what we see in brains.
The contribution of the paper, and its actual title is about the proposed mechanism.
All the comments amounting to ‘no shit, sherlock’, are about the mangled headline, not the paper.
Oh hey, I know one of the authors on this paper. I've been meaning to ask him at NeurIPS how this prospective configuration algorithm works for latent variable models.
Some 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.
Many of us whom are tired of that are both countering it and just using different terms for each where possible. So, I’m calling the AI’s models, saying model training instead of learning, and finding and acting on patterns in data. Even laypeople seem to understand these terms with less confusion about them being just like brains.
> 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" to "in a vaguely resembling or reminiscent way". The claim that artificial neural networks "work like the brain" is false under the first reading of "like" but true under the second.
> 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 -- simulate the same kind of thing that goes on in the brain. That is to say that the article posits that some set of weights would replicate the brain pretty closely. The issue is how to find those weights. Backprop is one of many known -- and used -- algorithms . It is liked because the mechanism is well understood (function minimization using calculus). There have been many other ways suggested to train ANNs (genetic algorithms, annealing, etc). This one suggests an energy based approach, which is also not novel.
The comments here saying this was obvious or something else more negative are disappointing. Neural networks are named for neurons in biological brains. There is a lot of inspiration in deep learning that comes from biology. So the association is there. Pretending you’re superior for knowing the two are still different, contributes nothing. Doing so in more specific ways, or attempting to further understand the differences between deep learning and biology through research, is useful.
Wait, 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 biological processes. From what I can tell, prosp. config learns by solving what the activations should have been to explain the error, and then updates the weights in accordance, which apparently somehow avoids abalating old associations. They then show how prosp. config explains observed biological processes. Cool stuff, wish I could find the code. There's some supplemental notes:
> Backprop can lead to 'catastrophic interference' where learning new things abalates old associations, which doesn't match observed biological processes.
Most people find that if you move away from a topic and into a new one your knowledge of it starts to decay over time. 20+ years ago I had a job as a Perl and VB6 developer, I think most of my knowledge of those languages has been evacuated to make way for all the other technologies I've learned since (and 20 years of life experiences). Isn't that an example of "learning new things ablates old associations"?
Claims that LLMs work like human brains were common at the start of this AI wave. There are still lots of fanboys who defend accusations of rampant copyright infringement with the claim that AI model training should be treated like human brain learning.
I did not read the article - but I guess it all depends on the level of abstraction we are talking about. There is a very abstract level where you can say that AI learns like a biological brain and there is a level where you would say that a particular human brain learns in a different way than another particular human brain.
> Do "AI" fanbois really think LLMs work like a biological brain?
If you read the article you'd know two things: (1) the article explicitly calls out Hopfield networks as being more bio-similar (Hopfield networks are intricately connected to attention layers) and (2) the overall architecture (the inference pass) of the networks studied here remain unmodified. Only the training mechanism changes.
As for a direct addressing of the claim... if the article is on point, then 'learning' has a much more encompassing physical manifestation than was previously thought. Really any system that self optimizes would be seen as bio-similar. In both mechanisms, there's a process to drive the system to 'convergence'. The issue is how fast that convergence is, not the end result.
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 and ANNs were previously unknown and is misleading IMO.
reply