Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911764674772992 |
|---|---|
| author | Picco, Enrico Jaurigue, Lina Lüdge, Kathy Massar, Serge |
| author_facet | Picco, Enrico Jaurigue, Lina Lüdge, Kathy Massar, Serge |
| contents | We present an experimental validation of a recently proposed optimization technique for reservoir computing, using an optoelectronic setup. Reservoir computing is a robust framework for signal processing applications, and the development of efficient optimization approaches remains a key challenge. The technique we address leverages solely a delayed version of the input signal to identify the optimal operational region of the reservoir, simplifying the traditionally time-consuming task of hyperparameter tuning. We verify the effectiveness of this approach on different benchmark tasks and reservoir operating conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14371 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input Picco, Enrico Jaurigue, Lina Lüdge, Kathy Massar, Serge Emerging Technologies Artificial Intelligence Neural and Evolutionary Computing Optics We present an experimental validation of a recently proposed optimization technique for reservoir computing, using an optoelectronic setup. Reservoir computing is a robust framework for signal processing applications, and the development of efficient optimization approaches remains a key challenge. The technique we address leverages solely a delayed version of the input signal to identify the optimal operational region of the reservoir, simplifying the traditionally time-consuming task of hyperparameter tuning. We verify the effectiveness of this approach on different benchmark tasks and reservoir operating conditions. |
| title | Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input |
| topic | Emerging Technologies Artificial Intelligence Neural and Evolutionary Computing Optics |
| url | https://arxiv.org/abs/2401.14371 |