News for hackers. Stuff that matters.
Re:Alice's adventures in a differentiable wonderland by srean on Friday May 03, 2024 @07:38AM (#40246497)
Sandpile mathematics, something that is studied by computer scientists and mathematicians, would be an approximation. Its not so much the level of the spike that matters but how often they spike is what conveys the signal. The temporal behavior is supremely important. It used to be believed that the rate is all that matters, but now, no longer.

There are ANN models that model these spike trains (that's what these 'avalanches' are called), these do work similar to real neurons, but they are not part of the deep neural network popularity [0,1]. Besides, backpropagation is not what goes on in the brain, its known to be biologically infeasible.

So all in all the traditional ANNs are nothing like real neural networks. That's ok, aeroplanes do not fly like birds, but they do still 'fly'.

[0] https://en.wikipedia.org/wiki/Spiking_neural_network

[1] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9313413/

There are no comments on this comment yet.