News for hackers. Stuff that matters.
Re:Deep physical neural networks trained with backpropagation by version_five on Saturday January 29, 2022 @12:48PM (#30128481)
I don't have a specific reference but I'd say it's a common knowledge assertion based on the growth in the number of parameters in models over the last 10 years. There are lots of places where you can see how the number of parameters, especially in language and vision models, has increased, and find that the amount of training time quoted. Normally it's framed in terms of compute instead of energy.

There are no comments on this comment yet.