KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks

Lukas Niehaus; Robin Rawiel; Ulf Krumnack

返回文献探索

Paper · arXiv 2610.20117

KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks

Lukas Niehaus, Robin Rawiel, Ulf Krumnack

3 upvotesOctober 14, 2026arXiv 预印本

AI 摘要

KANLab is an interactive browser tool for teaching Kolmogorov-Arnold Networks by visualizing B-spline activation curves, gradient descent, and pruning in a compact 2D setting.

Kolmogorov-Arnold NetworksB-spline activation curvestrainable control pointsgradient descentactivation varianceinteractive pruningresidual connectionslearnable scaling parameters

Abstract

KANLab is a browser-based visualization tool designed to interactively teach the core concepts of Kolmogorov-Arnold Networks (KAN), forked from the widely successful TensorFlow Playground. To maximize educational clarity, KANLab omits residual connections and learnable scaling parameters found in modern KAN implementations, ensuring that displayed B-spline activation curves directly correspond to their underlying trainable control points. Users can inspect and modify activation functions, initialization schemes and observe gradient descent correcting manual disruptions. Furthermore, user can explore phenomena such as activation variance, interactive pruning, and re\-/training within a compact 2D machine learning setting. KANLab is open-source and available at https://kanlab.app/