KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
Abstract
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.
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/
Community
Hi, author here 👋 KANLab is TensorFlow Playground for Kolmogorov-Arnold Networks: train a small KAN in your browser and watch every B-spline activation change as it learns.
🔗 Try it: https://kanlab.app
🤗 Space: https://huggingface.co/spaces/luniehaus/kanlab
💻 Code (Apache-2.0): https://github.com/lniehaus/kanlab
One deliberate design choice: we drop residual connections and learnable scaling, so each curve you see is its trainable control points. You can drag a control point and watch gradient descent pull it back, inspect activation variance, and prune and retrain.
We built it for teaching. Feedback is very welcome, especially from anyone covering KANs in a course.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials (2026)
- InKAN: B-Spline KANs via Truncated Power Form (2026)
- Evaluating the Effectiveness of SechKAN on 1D Data (2026)
- A KAN-based Non-linear Factorization for Embedding Layer Compression (2026)
- Kolmogorov-Arnold Networks for Personal Context Recognition on ExtraSensory (2026)
- Hybrid Parallel Bessel KAN Model: a Kolmogorov Arnold Network: integrated framework for developing a novel architecture to reconstruct the fused-basis approach via a parameter free quadratic interaction (2026)
- Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2610.20117 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper