KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
Not on the map. Why?
Abstract (arXiv)
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/
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 13 references that are in the map. First posted on arXiv 14 Oct 2026.
Builds on
9 of 13 references.
References · 9
- 2024KAN: Kolmogorov-Arnold Networkscited by 649
- 2024KAN or MLP: A Fairer Comparisoncited by 73
- 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 41
- 2017Direct-Manipulation Visualization of Deep Networkscited by 28
- 2024How to Learn More? Exploring Kolmogorov-Arnold Networks for Hyperspectral Image Classificationcited by 20
- 2025Initialization Schemes for Kolmogorov-Arnold Networks: An Empirical Studycited by 11
- 2025MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classificationcited by 9
- 2017Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learningcited by 8
- 2025Quantum Machine Learning Playgroundcited by 1
Built on by
Not cited yet.