News for hackers. Stuff that matters.
Re:Exploring Weight Agnostic Neural Networks by elcomet on Thursday August 29, 2019 @06:33AM (#20828277)
I'm not sure I understand what you're saying. I think you're talking about gradient descent, not rm autograd. Gradient descent, which is a breakthrough dates back to the 19th century. That's what allow us to approximate gradients. RM autograd is a clever implement detail of this (how to compute gradients efficiently).

There are no comments on this comment yet.