# KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks

arXiv: https://arxiv.org/abs/2610.20117 · HTML: https://mlsanity.com/paper/2610.20117/

## 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 (most cited first, 9 of 9)

- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [KAN or MLP: A Fairer Comparison](https://mlsanity.com/paper/2407.16674/) (2024)
- [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://mlsanity.com/paper/1809.01587/) (2018)
- [Direct-Manipulation Visualization of Deep Networks](https://mlsanity.com/paper/1708.03788/) (2017)
- [How to Learn More? Exploring Kolmogorov-Arnold Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2406.15719/) (2024)
- [Initialization Schemes for Kolmogorov-Arnold Networks: An Empirical Study](https://mlsanity.com/paper/2509.03417/) (2025)
- [MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classification](https://mlsanity.com/paper/2502.18416/) (2025)
- [Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning](https://mlsanity.com/paper/1708.00807/) (2017)
- [Quantum Machine Learning Playground](https://mlsanity.com/paper/2507.17931/) (2025)

## 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/