Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
Not on the map. Why?
Abstract (arXiv)
Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (arXiv:2404.19756). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (univariate real) functions and ReLU networks. We provide completely explicit constructions to convert a piecewise linear KAN into a ReLU network and vice versa.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 3 Mar 2025.
Builds on
15 of 35 references.
References · 15
- 2017Attention Is All You Needcited by 59,932
- 2014On the Number of Linear Regions of Deep Neural Networkscited by 378
- 2016On the Expressive Power of Deep Neural Networkscited by 302
- 2016Understanding Deep Neural Networks with Rectified Linear Unitscited by 253
- 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
- 2020The Kolmogorov-Arnold representation theorem revisitedcited by 89
- 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
- 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
- 2023Hidden symmetries of ReLU networkscited by 38
- 2020Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplificationcited by 32
- 2018Empirical Bounds on Linear Regions of Deep Rectifier Networkscited by 23
- 2022Algorithmic Determination of the Combinatorial Structure of the Linear Regions of ReLU Neural Networkscited by 21
3 more
- 2023On the Kolmogorov neural networkscited by 19
- 2023Polyhedral Complex Extraction from ReLU Networks using Edge Subdivisioncited by 14
- 2023Any Deep ReLU Network is Shallowcited by 6
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.