News for hackers. Stuff that matters.
Re:Tversky Neural Networks by sdenton4 on Sunday August 17, 2025 @08:30AM (#44931149)
It's wishful thinking.

Neutral networks need to be over parameterized to find good solutions, meaning there is a surface of solutions. The optimization procedure tries to walk towards that surface as quickly as possible, and tend to find a low-energy point on the surface of solutions. In particular, a low energy solution isn't sparse, and therefore isn't interpretable.

Re:Tversky Neural Networks by c32c33429009ed6 on Sunday August 17, 2025 @08:52AM (#44931239)
Interesting; can you provide some references for this way of thinking?