Re:A visual proof that neural nets can compute any function
by sdenton4 on Sunday March 06, 2022 @11:03AM
(#30578442)
You've got a kind of narrow view of the matter... The need for interactive understanding is addressed in different ways by reinforcement learning, GANs, and autoregressive recurrent neutral networks.
In the latter cases, the generative output of the network is a kind of experiment, and back prop from the loss function provides a route to improvement.
I think it's an unfortunate historical accident that the field of machine learning is so transfixed with classifiers. But they're really not the only game in town.
In the latter cases, the generative output of the network is a kind of experiment, and back prop from the loss function provides a route to improvement.
I think it's an unfortunate historical accident that the field of machine learning is so transfixed with classifiers. But they're really not the only game in town.