Universality of reservoir systems with recurrent neural networks
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_ | 1866913778908528640 |
|---|---|
| author | Yasumoto, Hiroki Tanaka, Toshiyuki |
| author_facet | Yasumoto, Hiroki Tanaka, Toshiyuki |
| contents | Approximation capability of reservoir systems whose reservoir is a recurrent neural network (RNN) is discussed. We show what we call uniform strong universality of RNN reservoir systems for a certain class of dynamical systems. This means that, given an approximation error to be achieved, one can construct an RNN reservoir system that approximates each target dynamical system in the class just via adjusting its linear readout. To show the universality, we construct an RNN reservoir system via parallel concatenation that has an upper bound of approximation error independent of each target in the class. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Universality of reservoir systems with recurrent neural networks Yasumoto, Hiroki Tanaka, Toshiyuki Neural and Evolutionary Computing Machine Learning Approximation capability of reservoir systems whose reservoir is a recurrent neural network (RNN) is discussed. We show what we call uniform strong universality of RNN reservoir systems for a certain class of dynamical systems. This means that, given an approximation error to be achieved, one can construct an RNN reservoir system that approximates each target dynamical system in the class just via adjusting its linear readout. To show the universality, we construct an RNN reservoir system via parallel concatenation that has an upper bound of approximation error independent of each target in the class. |
| title | Universality of reservoir systems with recurrent neural networks |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2403.01900 |