Re:Scientists watch a memory form in the brain of a living fish
by igorkraw on Sunday March 06, 2022 @08:13AM
(#30577364)
Artificial neural networks have something similar, called the lottery ticket hypothesis
Re:Scientists watch a memory form in the brain of a living fish
by sva_ on Sunday March 06, 2022 @10:10AM
(#30578027)
I'm not sure it is quite comparable, as the lottery hypothesis postulates that for every Neural Net with n connections/weights, there is one with n-1 connections, that retains its accuracy. So it doesn't learn by pruning, just becomes more efficient by being smaller. That's at least how I understood it.
Re:Scientists watch a memory form in the brain of a living fish
by igorkraw on Sunday March 06, 2022 @05:20PM
(#30581846)
Your thing would imply a 0 connected neural net could compete with GPT3. I quote
The Lottery Ticket Hypothesis: A randomly-initialized, dense neural network contains a subnetwork that is initialised such that — when trained in isolation — it can match the test accuracy of the original network after training for at most the same number of iterations. - Frankle & Carbin (2019, p.2)
Re:Scientists watch a memory form in the brain of a living fish
by sva_ on Sunday March 06, 2022 @06:01PM
(#30582152)
Yeah, that's why it is merely a hypothesis. I think the Lottery Ticket hypothesis goes further and states that this subnetwork also has a subnetwork which matches test accuracy, up to some degree. Else it wouldn't be interesting. Of course there must be a limit...
Re:Scientists watch a memory form in the brain of a living fish
by igorkraw on Monday March 07, 2022 @01:44AM
(#30584853)
The interesting bit is that you don't need to tweak the subnet, only remove the other noisy connections. If you remove capacity, at some point test accuracy needs to go down. The hypothesis is about the idea that we maybe don't "train" the weights, we "find" them, not about unlimited nesting (as far as I understand it, but I have high confidence. Happy to be proven wrong tho)
I think part of learning is, that we have some general idea about something, but it turns out to be inaccurate, so we need to specialize it (and get rid off the old connection.) I'm speculating though.
I'm a bit confused by the "replanted in others" part though. I'd assume, overall, there is a net loss of synapses when learning (and hence learning becomes more difficult as we age - there just isn't enough entropy to prune away.)
See also https://www.tcd.ie/news_events/articles/why-do-we-forget-new...
And Discussion https://news.ycombinator.com/item?id=29940435
The article also has some older references - the idea isn't new.