A correspondence between Hebbian unlearning and steady states generated by nonequilibrium dynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929533452550144 |
|---|---|
| author | Behera, Agnish Kumar Du, Matthew Jagadisan, Uday Sastry, Srikanth Rao, Madan Vaikuntanathan, Suriyanarayanan |
| author_facet | Behera, Agnish Kumar Du, Matthew Jagadisan, Uday Sastry, Srikanth Rao, Madan Vaikuntanathan, Suriyanarayanan |
| contents | The classic paradigms for learning and memory recall focus on strengths of synaptic couplings and how these can be modulated to encode memories. In a previous paper [A. K. Behera, M. Rao, S. Sastry, and S. Vaikuntanathan, Physical Review X 13, 041043 (2023)], we demonstrated how a specific non-equilibrium modification of the dynamics of an associative memory system can lead to increase in storage capacity. In this work, using analytical theory and computational inference schemes, we show that the dynamical steady state accessed is in fact similar to those accessed after the operation of a classic unsupervised scheme for improving memory recall, Hebbian unlearning or ``dreaming". Together, our work suggests how nonequilibrium dynamics can provide an alternative route for controlling the memory encoding and recall properties of a variety of synthetic (neuromorphic) and biological systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06269 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A correspondence between Hebbian unlearning and steady states generated by nonequilibrium dynamics Behera, Agnish Kumar Du, Matthew Jagadisan, Uday Sastry, Srikanth Rao, Madan Vaikuntanathan, Suriyanarayanan Disordered Systems and Neural Networks Statistical Mechanics The classic paradigms for learning and memory recall focus on strengths of synaptic couplings and how these can be modulated to encode memories. In a previous paper [A. K. Behera, M. Rao, S. Sastry, and S. Vaikuntanathan, Physical Review X 13, 041043 (2023)], we demonstrated how a specific non-equilibrium modification of the dynamics of an associative memory system can lead to increase in storage capacity. In this work, using analytical theory and computational inference schemes, we show that the dynamical steady state accessed is in fact similar to those accessed after the operation of a classic unsupervised scheme for improving memory recall, Hebbian unlearning or ``dreaming". Together, our work suggests how nonequilibrium dynamics can provide an alternative route for controlling the memory encoding and recall properties of a variety of synthetic (neuromorphic) and biological systems. |
| title | A correspondence between Hebbian unlearning and steady states generated by nonequilibrium dynamics |
| topic | Disordered Systems and Neural Networks Statistical Mechanics |
| url | https://arxiv.org/abs/2410.06269 |