Reservoir computing is a term used to describe a class of machine learning algorithms that rely on transient dynamics of a dynamical system to implement and manipulate goal-related information.
The most famous example is echo-state networks, which uses random recurrent neural networks as reservoirs, but other dynamical systems can also be used.
Reservoir computing with cellular automata
Reservoir computing can use cellular automata as the reservoir. Some citations (Nichele and Molund 2017; Yilmaz 2014; Morán, Frasser, and Rosselló 2018; Babson, Teuscher, and 2019).
Echo-state networks
Reservoir computing for differential equation solving
(Mattheakis, Joy, and Protopapas 2021)
Bibliography
- Babson, Neil, Christof Teuscher, and . December 15, 2019. "Reservoir Computing with Complex Cellular Automata". Complex Systems 28 (4):433–55. DOI.
- Mattheakis, Marios, Hayden Joy, and Pavlos Protopapas. August 25, 2021. “Unsupervised Reservoir Computing for Solving Ordinary Differential Equations”. arXiv:2108.11417 [Physics]. http://arxiv.org/abs/2108.11417.
- Morán, Alejandro, Christiam F. Frasser, and Josep L. Rosselló. June 21, 2018. “Reservoir Computing Hardware with Cellular Automata”. arXiv:1806.04932 [Nlin]. http://arxiv.org/abs/1806.04932.
- Nichele, Stefano, and Andreas Molund. March 8, 2017. “Deep Reservoir Computing Using Cellular Automata”. arXiv:1703.02806 [Cs]. http://arxiv.org/abs/1703.02806.
- Yilmaz, Ozgur. October 1, 2014. “Reservoir Computing Using Cellular Automata”. arXiv:1410.0162 [Cs]. http://arxiv.org/abs/1410.0162.