KAN 2.0: Kolmogorov-Arnold Networks Meet Science
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909290854350848 |
|---|---|
| author | Liu, Ziming Ma, Pingchuan Wang, Yixuan Matusik, Wojciech Tegmark, Max |
| author_facet | Liu, Ziming Ma, Pingchuan Wang, Yixuan Matusik, Wojciech Tegmark, Max |
| contents | A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold Networks (KANs) and science. The framework highlights KANs' usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in the pykan package: (1) MultKAN: KANs with multiplication nodes. (2) kanpiler: a KAN compiler that compiles symbolic formulas into KANs. (3) tree converter: convert KANs (or any neural networks) to tree graphs. Based on these tools, we demonstrate KANs' capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10205 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KAN 2.0: Kolmogorov-Arnold Networks Meet Science Liu, Ziming Ma, Pingchuan Wang, Yixuan Matusik, Wojciech Tegmark, Max Machine Learning Artificial Intelligence Computational Physics Data Analysis, Statistics and Probability A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold Networks (KANs) and science. The framework highlights KANs' usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in the pykan package: (1) MultKAN: KANs with multiplication nodes. (2) kanpiler: a KAN compiler that compiles symbolic formulas into KANs. (3) tree converter: convert KANs (or any neural networks) to tree graphs. Based on these tools, we demonstrate KANs' capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws. |
| title | KAN 2.0: Kolmogorov-Arnold Networks Meet Science |
| topic | Machine Learning Artificial Intelligence Computational Physics Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2408.10205 |