SymFlux: deep symbolic regression of Hamiltonian vector fields
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913933162446848 |
|---|---|
| author | Evangelista-Alvarado, M. A. Suárez-Serrato, P. |
| author_facet | Evangelista-Alvarado, M. A. Suárez-Serrato, P. |
| contents | We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybrid CNN-LSTM architectures to learn and output the symbolic mathematical expression of the underlying Hamiltonian. Training and validation are conducted on newly developed datasets of Hamiltonian vector fields, a key contribution of this work. Our results demonstrate the model's effectiveness in accurately recovering these symbolic expressions, advancing automated discovery in Hamiltonian mechanics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06342 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SymFlux: deep symbolic regression of Hamiltonian vector fields Evangelista-Alvarado, M. A. Suárez-Serrato, P. Machine Learning Artificial Intelligence Dynamical Systems Symplectic Geometry We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybrid CNN-LSTM architectures to learn and output the symbolic mathematical expression of the underlying Hamiltonian. Training and validation are conducted on newly developed datasets of Hamiltonian vector fields, a key contribution of this work. Our results demonstrate the model's effectiveness in accurately recovering these symbolic expressions, advancing automated discovery in Hamiltonian mechanics. |
| title | SymFlux: deep symbolic regression of Hamiltonian vector fields |
| topic | Machine Learning Artificial Intelligence Dynamical Systems Symplectic Geometry |
| url | https://arxiv.org/abs/2507.06342 |