News for hackers. Stuff that matters.
Re:Deep physical neural networks trained with backpropagation by davesque on Saturday January 29, 2022 @02:31PM (#30129576)
I think they may have provided fewer citations because it felt like a less controversial claim. I think the choice of words was just a bit awkward. To me, it seems like they were asserting that deep learning requires lots of computational resources which is common knowledge. In general, this translates to higher energy requirements.

There are no comments on this comment yet.