Symbolic KANs for Interpretable Learning

Symbolic Kolmogorov-Arnold Networks (Symbolic-KANs) embeds symbolic structure directly within a trainable network.

Symbolic-KANs represent multivariate functions as compositions of learned univariate primitives applied to learned scalar projections, guided by a library of analytic functions, hierarchical gating, and symbolic regularization that progressively sharpens continuous mixtures into one-hot selections. After training, each active unit selects a single primitive and projection direction, producing compact closed-form expressions without post-hoc symbolic fitting.

This file-exchange provides partial implementation of Symbolic-KANs using Deep Learning Toolbox based on Pub_Symbolic_KANs