SOURCE-LINKED INTELLIGENCE

RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Kolmogorov--Arnold Networks (KANs) replace the fixed scalar weights of a standard network with learnable univariate functions on each edge, but existing variants still fix the \emph{basis} that those functions are built from: B-splines, Chebyshev polynomials, wavelets, or Jacobi polynomials, and learn only the combination weights over it. We introduce RecKAN, which instead defines the basis itself by a second order polynomial recurrence, $R_{n+1}(x) = (ax^2+bx+c)R_n(x) + (dx+e)R_{n-1}(x)$, whose five coefficients are learned jointly with the network. We show this recurrence recovers several cl

Read original source ↗ Open in workspace

recordType

paper

region

Global