News for hackers. Stuff that matters.
Re:Deep physical neural networks trained with backpropagation by visarga on Saturday January 29, 2022 @04:13PM (#30130519)
> When I read the headline I imagined they had implemented back propagation in a physical system

They touch on that by observing you could train a second physical neural network to compute the gradients for the first. So it could all be physical.

> Improvements to PAT could extend the utility of PNNs. For example, PAT’s backward pass could be replaced by a neural network that directly estimates parameter updates for the physical system. Implementing this ‘teacher’ neural network with a PNN would allow subsequent training to be performed without digital assistance.

So you need to use in silico training a at first, but can get rid of it in deployment.

There are no comments on this comment yet.