Revisiting multifunctionality in reservoir computing
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_ | 1866915247678291968 |
|---|---|
| author | Mandal, Swarnendu Aihara, Kazuyuki |
| author_facet | Mandal, Swarnendu Aihara, Kazuyuki |
| contents | Multifunctionality is ubiquitous in biological neurons. Several studies have translated the concept to artificial neural networks as well. Recently, multifunctionality in reservoir computing (RC) has gained the widespread attention of researchers. Multistable dynamics of the reservoir can be configured to capture multiple tasks, each by one of the co-existing attractors. However, there are several limitations in the applicability of this approach. So far, multifunctional RC has been shown to be able to reconstruct different attractor climates only when the attractors are well separated in the phase space. We propose a more flexible reservoir computing scheme capable of multifunctioning beyond the earlier limitations. The proposed architecture holds striking similarity with the multifunctional biological neural networks and showcases superior performance. It is capable of learning multiple chaotic attractors with overlapping phase space. We successfully train the RC to achieve multifunctionality with wide range of tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12621 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revisiting multifunctionality in reservoir computing Mandal, Swarnendu Aihara, Kazuyuki Chaotic Dynamics Multifunctionality is ubiquitous in biological neurons. Several studies have translated the concept to artificial neural networks as well. Recently, multifunctionality in reservoir computing (RC) has gained the widespread attention of researchers. Multistable dynamics of the reservoir can be configured to capture multiple tasks, each by one of the co-existing attractors. However, there are several limitations in the applicability of this approach. So far, multifunctional RC has been shown to be able to reconstruct different attractor climates only when the attractors are well separated in the phase space. We propose a more flexible reservoir computing scheme capable of multifunctioning beyond the earlier limitations. The proposed architecture holds striking similarity with the multifunctional biological neural networks and showcases superior performance. It is capable of learning multiple chaotic attractors with overlapping phase space. We successfully train the RC to achieve multifunctionality with wide range of tasks. |
| title | Revisiting multifunctionality in reservoir computing |
| topic | Chaotic Dynamics |
| url | https://arxiv.org/abs/2504.12621 |