Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems — mentioned by akdom

Sat, 08 Jun 2024 15:02:53 GMT

Specifically to the point of the comparatively low reliability / high variation of analog systems: an interesting property of neural nets is that they can be robust relative to noise when trained with the same type of noise witnessed under inference. Whether or not speed/etc. would be better in the digital vs. analog design-space, it's an interesting thing to consider that neural nets can automatically account for the encoding-medium's variability. This perhaps makes neural solutions a good fit for low power analog media which otherwise aren't useful for classical computing. See…

Paper and discussion history. A mention is not an endorsement.

Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems — mentioned by rch

Sun, 30 May 2021 20:19:37 GMT

The paper is linked at the bottom of the article: Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems -- https://arxiv.org/abs/2104.13386 > physics-aware training (PAT)... allows us to efficiently and accurately execute the backpropagation algorithm on any sequence of physical input-output transformations, directly in situ.

Paper and discussion history. A mention is not an endorsement.

Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems · HackerPapers discussions

Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems — mentioned by akdom

Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems — mentioned by rch