Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation
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_ | 1866912057707724800 |
|---|---|
| author | Wang, Qingshan Wanjura, Clara C. Marquardt, Florian |
| author_facet | Wang, Qingshan Wanjura, Clara C. Marquardt, Florian |
| contents | Given the rapidly growing scale and resource requirements of machine learning applications, the idea of building more efficient learning machines much closer to the laws of physics is an attractive proposition. One central question for identifying promising candidates for such neuromorphic platforms is whether not only inference but also training can exploit the physical dynamics. In this work, we show that it is possible to successfully train a system of coupled phase oscillators - one of the most widely investigated nonlinear dynamical systems with a multitude of physical implementations, comprising laser arrays, coupled mechanical limit cycles, superfluids, and exciton-polaritons. To this end, we apply the approach of equilibrium propagation, which permits to extract training gradients via a physical realization of backpropagation, based only on local interactions. The complex energy landscape of the XY/ Kuramoto model leads to multistability, and we show how to address this challenge. Our study identifies coupled phase oscillators as a new general-purpose neuromorphic platform and opens the door towards future experimental implementations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08579 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation Wang, Qingshan Wanjura, Clara C. Marquardt, Florian Emerging Technologies Disordered Systems and Neural Networks Mesoscale and Nanoscale Physics Neural and Evolutionary Computing Optics Given the rapidly growing scale and resource requirements of machine learning applications, the idea of building more efficient learning machines much closer to the laws of physics is an attractive proposition. One central question for identifying promising candidates for such neuromorphic platforms is whether not only inference but also training can exploit the physical dynamics. In this work, we show that it is possible to successfully train a system of coupled phase oscillators - one of the most widely investigated nonlinear dynamical systems with a multitude of physical implementations, comprising laser arrays, coupled mechanical limit cycles, superfluids, and exciton-polaritons. To this end, we apply the approach of equilibrium propagation, which permits to extract training gradients via a physical realization of backpropagation, based only on local interactions. The complex energy landscape of the XY/ Kuramoto model leads to multistability, and we show how to address this challenge. Our study identifies coupled phase oscillators as a new general-purpose neuromorphic platform and opens the door towards future experimental implementations. |
| title | Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation |
| topic | Emerging Technologies Disordered Systems and Neural Networks Mesoscale and Nanoscale Physics Neural and Evolutionary Computing Optics |
| url | https://arxiv.org/abs/2402.08579 |