A note on the physical interpretation of neural PDE's
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909777527832576 |
|---|---|
| author | Succi, Sauro |
| author_facet | Succi, Sauro |
| contents | We highlight a formal and substantial analogy between Machine Learning (ML) algorithms and discrete dynamical systems (DDS) in relaxation form. The analogy offers a transparent interpretation of the weights in terms of physical information-propagation processes and identifies the model function of the forward ML step with the local attractor of the corresponding discrete dynamics. Besides improving the explainability of current ML applications, this analogy may also facilitate the development of a new class ML algorithms with a reduced number of weights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06739 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A note on the physical interpretation of neural PDE's Succi, Sauro Machine Learning Disordered Systems and Neural Networks Computational Physics We highlight a formal and substantial analogy between Machine Learning (ML) algorithms and discrete dynamical systems (DDS) in relaxation form. The analogy offers a transparent interpretation of the weights in terms of physical information-propagation processes and identifies the model function of the forward ML step with the local attractor of the corresponding discrete dynamics. Besides improving the explainability of current ML applications, this analogy may also facilitate the development of a new class ML algorithms with a reduced number of weights. |
| title | A note on the physical interpretation of neural PDE's |
| topic | Machine Learning Disordered Systems and Neural Networks Computational Physics |
| url | https://arxiv.org/abs/2502.06739 |