News for hackers. Stuff that matters.
Re:Deep physical neural networks trained with backpropagation by visarga on Saturday January 29, 2022 @04:32PM (#30130727)
If you can train a non-linear physical system with this method, in principle, you could also train real brains. You can't update the parameters of the brain, but you can inject signal. Assuming real brains to be black box functions for which you could learn a noisy estimator of gradients, it could be used for neural implants that supplement lost brain functionality, or a Matrix-like skill loading system.
Re:Deep physical neural networks trained with backpropagation by phreeza on Sunday January 30, 2022 @03:28AM (#30135082)
You need a differentiable forward model of the process, which is not available for the human brain.