News for hackers. Stuff that matters.
Re:Double Descent in Human Learning by arthur2e5 on Thursday April 27, 2023 @03:42AM (#35724568)
It can be argued that the human case correlates better with the "data double descent" model, assuming the brain network size does not change. The thing is... it does! It goes up and down as connections grow and get pruned. Biology is messy. Biological analogies can never be perfectly clean, especially for a system as giant as a human.

There are no comments on this comment yet.