Tootfinder

oooh! seem like there's a new, promising neural-net-like architecture: #KAN (Kolmogorov-Arnold Networks).
and they are actually pretty easy to understand, too 👀!
instead of fixed nonlinearities on the nodes and learnable linear weights, edges are are learnable nonlinearities (using splines) and the nodes simply add.
well i'm not exactly sure how the training works yet, but i g…

KAN: Kolmogorov-Arnold Networks
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of ac…

Später #Fensterfreitag