The reviewed record of science sign in
Pith

arxiv: 2405.06721 · v1 · pith:HITFLIPW · submitted 2024-05-10 · cs.LG · cs.AI

Kolmogorov-Arnold Networks are Radial Basis Function Networks

Reviewed by Pithpith:HITFLIPWopen to challenge →

classification cs.LG cs.AI
keywords basisnetworksradialfunctionkolmogorov-arnoldapproximatedb-splinesdoing
0
0 comments X
read the original abstract

This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions. Doing so leads to FastKAN, a much faster implementation of KAN which is also a radial basis function (RBF) network.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. KANs need curvature: penalties for compositional smoothness

    cs.LG 2026-05 unverdicted novelty 7.0

    A curvature penalty for KANs, derived to respect compositional effects and equipped with a proven upper bound on full-model curvature, produces smoother activations while preserving accuracy.

  2. Autocorrelation Reintroduces Spectral Bias in KANs for Time Series Forecasting

    cs.LG 2026-04 unverdicted novelty 7.0

    Temporal autocorrelation reintroduces spectral bias in KANs for time series forecasting, which DCT preprocessing can mitigate.

  3. In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks

    cs.LG 2026-03 unverdicted novelty 7.0

    In-context symbolic regression methods improve robustness of symbolic formula recovery from KANs, cutting median OFAT test MSE by up to 99.8 percent across hyperparameter sweeps.

  4. Kolmogorov-Arnold Chemical Reaction Neural Networks for learning pressure-dependent kinetic rate laws

    physics.chem-ph 2025-11 unverdicted novelty 7.0

    KA-CRNNs learn pressure-dependent and collider-specific kinetic rate laws from data using Kolmogorov-Arnold activations inside a CRNN framework, outperforming interpolative methods by 2.88x in MSE on two proof-of-conc...

  5. Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

    cs.CV 2026-06 unverdicted novelty 6.0

    Structural KAN convolutions with shared value functions or wavelet-based adaptive filter shapes match or exceed per-edge KAN accuracy on CIFAR at 0.4M parameters.

  6. Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks

    stat.ML 2026-05 unverdicted novelty 6.0

    Adaptive RBF-KAN adds multiple radial basis kernels and LOOCV-based shape initialization to FastKAN, with benchmark tests on 2D functions showing kernel-specific advantages for smooth, discontinuous, and oscillatory cases.

  7. KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

    cs.AI 2026-05 conditional novelty 6.0

    A hybrid KAN-MLP model for IMU-based human activity recognition achieves 5.33% relative macro F1 improvement over pure MLPs on eight datasets by placing KANs at input embedding and classification stages.

  8. Partition-of-Unity Gaussian Kolmogorov-Arnold Networks

    cs.CE 2026-04 unverdicted novelty 6.0

    PU-GKAN applies Shepard normalization to Gaussian bases in KANs, yielding exact constant reproduction, reduced epsilon sensitivity, and better validation accuracy across tested regimes.

  9. Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks

    cs.CE 2026-04 unverdicted novelty 6.0

    A stable operating interval for the Gaussian scale parameter ε in KANs is ε ∈ [1/(G-1), 2/(G-1)], derived from first-layer feature geometry and validated across multiple approximation and physics-informed problems.

  10. Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks

    cs.LG 2026-04 unverdicted novelty 6.0

    Derives generalized formulas for KAN inference complexity using RM, BOP, and NABS metrics across B-spline, GRBF, Chebyshev, and Fourier variants.

  11. KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

    cs.AI 2026-05 unverdicted novelty 5.0

    A hybrid KAN-MLP architecture with KAN input embedding and specialized LarctanKAN classification layer yields 5.33% average macro F1 gain over pure-MLP baselines in IMU-based human activity recognition.

  12. Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches

    math.NA 2026-04 unverdicted novelty 5.0

    The work introduces a modulation-based analytical method for singularity proofs in singular PDEs and refines ML techniques like PINNs and KANs to identify blowup solutions, with application to the open 3D Keller-Segel...

  13. Optimized Architectures for Kolmogorov-Arnold Networks

    cs.LG 2025-12 unverdicted novelty 5.0

    Overprovisioned KANs with sparsification, deep supervision, and depth selection under differentiable MDL yield smaller models with competitive accuracy on benchmarks.

  14. KANLib -- A Modular, Extensible and Fast Kolmogorov-Arnold Network Implementation

    cs.LG 2026-06 unverdicted novelty 4.0

    KANLib is a unified, extensible KAN framework supporting adaptive grids and basis functions that reproduces reference performance on the California Housing benchmark with competitive speed.

  15. Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning

    cs.LG 2026-06 unverdicted novelty 4.0

    Hierarchical radial-basis-function Kolmogorov-Arnold networks are introduced with proofs of universal approximation for functions and random fields under Wasserstein-2 distance.

  16. A Practitioner's Guide to Kolmogorov-Arnold Networks

    cs.LG 2025-10 accept novelty 3.0

    A systematic review of Kolmogorov-Arnold Networks that maps their relation to Kolmogorov superposition theory, MLPs, and kernels, examines basis-function design choices, summarizes performance advances, and supplies a...