AI RESEARCH
Partition-of-Unity Gaussian Kolmogorov-Arnold Networks
arXiv CS.AI
•
ArXi:2604.23599v1 Announce Type: cross Gaussian basis functions provide an efficient and flexible alternative to spline activations in KANs. In this work, we We formulate both the standard Gaussian KAN (GKAN) and PU-GKAN from a finite-feature and additive-kernel viewpoint, making the induced layer kernels and empirical feature matrices explicit.