Re:Computational Model Reveals How the Brain Manages Short-T...
by bra-ket on Tuesday December 29, 2020 @01:13AM
(#25567248)
Oh god, what he calls constraints are the "spiking
nature of biological neurons", then he happily proceeds, just like you'd guess, to create this abomination of 'spiking RNN' and train this pretty much plain vanilla RNN via backpropagation, completely disregarding the energy spent, learning mechanism, and actual biological plausibility or relevance of this horrendous architecture as memory model.
The first author knows just enough to be dangerous.
>Sejnowski fell asleep
it surely looks like it
Re:Computational Model Reveals How the Brain Manages Short-T...
by subroutine on Tuesday December 29, 2020 @08:37PM
(#25577342)
Dropping a link below in case you're interested - I have a side-project that takes a more literal approach to modeling biologically plausible neural networks (MCMC simulations inside 3D models)...
https://www.pnas.org/content/pnas/116/45/22811.full.pdf
I'm not fully sold on this model, but the article is fairly dense and I dont fully understand it. (Sejnowski, the senior author, was on my dissertation committee; he fell asleep during my defense lol)