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

Inferring neural activity before plasticity for learning beyond backpropagation

nature.com

Post reply on HN
Print view View original

31–40 of 50 posts

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#31

Post by mrfox321 »

dawnofdusk wrote: post #29
lukeinator42 wrote: post #19

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…

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…

Second order methods, and their approximations, can be used in weight updating, too.

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#32

Post by skissane »

TheOtherHobbes wrote: post #30
skissane wrote: post #18

Earlier quoted context omitted.

> 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…

Is it replaced, or does it decay without reinforcement?

How can we distinguish those two possibilities?

Stuff like childhood memories seems very deeply ingrained even if rarely or never reinforced. I can still remember the phone number of our house we moved out of in 1991, when I was 8 or 9. If I’m still alive in 30/40/50 years time, I expect I’ll still remember it then.

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#33

Post by ergonaught »

lukeinator42 wrote: post #19

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…

> 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.

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#34

Post by utopicwork »

skissane wrote: post #12
nickpsecurity wrote: post #7

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. M…

> 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"…

[dead]

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#35

Post by perching_aix »

ergonaught wrote: post #33
lukeinator42 wrote: post #19

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…

> 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.

"differs fundamentally", being in the tense that it is, with the widely known context that AI is "modeled after the brain", definitely does suggest that oh no, they got the brain wrong when that modelling happened, therefore AI is fundamentally built wrong. Or at least I can definitely see this angle in it.

The angle I actually see in it though is the typical pitiful appeal to the idea that the brain is this incredible thing we should never hope to unravel, that AI bad, and that everyone working on AI is an idiot as per the link (and then the link painting a leaps and bounds more nuanced picture).

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#36

Post by robwwilliams »

Not my area of expertise, but this paper may be important for the reason that it is more closely aligned with the “enactive” paradigm of understand brain-body-behavior and learning than a backpropogation-only paradigm.

(I like enactive models of perception such as those advocated by Alva Noe, Humberto Maturana, Francisco Valera, and others. They get us well beyond the straightjacket of Cartesian dualism.)

Rather than have error signals tweak synaptic weights after a behavior, a cognitive system generates a set of actions it predicts will accommodate needs. This can apparently be accomplished without requiring short term synaptic plasticity. Then if all is good, weights are modified in a secondary phase that is more about asserting utility of the “test” response. More selection than descent. The emphasis is more on feedforward modulation and selection. Clearly there must be error signal feedback so some if you may argue that the distinction will be blurry at some levels. Agreed.

Look forward to reading more carefully to see how far off-base I am.

Re: Inferring neural activity before plasticity for learning beyond backpropagation

#37

Post by nickpsecurity »

skissane wrote: post #12
nickpsecurity wrote: post #7

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. M…

> 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 learning makes their training much more efficient. Even if a global mechanism exists (eg during sleep?), brain architectures could run through more training data faster and cheaper. Expensive step just tidies it up in shorter periods of time.

They are also more analog, parallel, sparse, and flexible. They have feedback loops (IIRC). Multiple tiers of memory integrated with their internal representation with hallucination mitigation. They also have many specialized components that automatically coordinate to do the work without being externally trained to. All in around 100 watts.

Brains are both different from and vastly superior to ANN’s. Similarities do exist, though. They both have cells, connections, and change connections based on incoming data. Quite abstract. Past that, I’m not sure what other similarities they have. Some non-brain-inspired ANN’s have memory in some form but I don’t know if it’s as effective and integrated as the brain’s yet.

Post reply on HN