On when is Reservoir Computing with Cellular Automata Beneficial?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910526354751488 |
|---|---|
| author | Glover, Tom Osipov, Evgeny Nichele, Stefano |
| author_facet | Glover, Tom Osipov, Evgeny Nichele, Stefano |
| contents | Reservoir Computing with Cellular Automata (ReCA) is a relatively novel and promising approach. It consists of 3 steps: an encoding scheme to inject the problem into the CA, the CA iterations step itself and a simple classifying step, typically a linear classifier. This paper demonstrates that the ReCA concept is effective even in arguably the simplest implementation of a ReCA system. However, we also report a failed attempt on the UCR Time Series Classification Archive where ReCA seems to work, but only because of the encoding scheme itself, not in any part due to the CA. This highlights the need for ablation testing, i.e., comparing internally with sub-parts of one model, but also raises an open question on what kind of tasks ReCA is best suited for. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09501 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On when is Reservoir Computing with Cellular Automata Beneficial? Glover, Tom Osipov, Evgeny Nichele, Stefano Neural and Evolutionary Computing Artificial Intelligence Emerging Technologies Reservoir Computing with Cellular Automata (ReCA) is a relatively novel and promising approach. It consists of 3 steps: an encoding scheme to inject the problem into the CA, the CA iterations step itself and a simple classifying step, typically a linear classifier. This paper demonstrates that the ReCA concept is effective even in arguably the simplest implementation of a ReCA system. However, we also report a failed attempt on the UCR Time Series Classification Archive where ReCA seems to work, but only because of the encoding scheme itself, not in any part due to the CA. This highlights the need for ablation testing, i.e., comparing internally with sub-parts of one model, but also raises an open question on what kind of tasks ReCA is best suited for. |
| title | On when is Reservoir Computing with Cellular Automata Beneficial? |
| topic | Neural and Evolutionary Computing Artificial Intelligence Emerging Technologies |
| url | https://arxiv.org/abs/2407.09501 |