#kan
1 post · all tags
-
· Kolmogorov-Arnold Networks
I have been playing with some implementations of Kolmogorov-Arnold Networks (KANs), the architecture Liu et al. proposed in April 2024. The pitch is simple and a bit provocative: take an MLP, move the nonlinearities from the nodes to the edges, and make them learnable. Every weight becomes a small univariate function, parameterized as a spline. The paper claimed better accuracy per parameter than MLPs, faster neural scaling laws, and networks you can read off as symbolic formulas.