Reservoir computing using nonuniform binary cellular automata

DOI10.25088/COMPLEXSYSTEMS.26.3.225MaRDI QIDQ5126836zbMATH OpenOpenAlexFDO

Authors Stefano Nichele, Magnus S. Gundersen

Publication date 20 October 2020

Published in Complex Systems (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1702.03812

Mathematics Subject Classification ID

Dynamical aspects of cellular automata (37B15) Cellular automata (computational aspects) (68Q80) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: The Reservoir Computing (RC) paradigm utilizes a dynamical system, i.e., a reservoir, and a linear classifier, i.e., a read-out layer, to process data from sequential classification tasks. In this paper the usage of Cellular Automata (CA) as a reservoir is investigated. The use of CA in RC has been showing promising results. In this paper, selected state-of-the-art experiments are reproduced. It is shown that some CA-rules perform better than others, and the reservoir performance is improved by increasing the size of the CA reservoir itself. In addition, the usage of parallel loosely coupled CA-reservoirs, where each reservoir has a different CA-rule, is investigated. The experiments performed on quasi-uniform CA reservoir provide valuable insights in CA reservoir design. The results herein show that some rules do not work well together, while other combinations work remarkably well. This suggests that non-uniform CA could represent a powerful tool for novel CA reservoir implementations.

Recommendations

• Reservoir Computing with Complex Cellular Automata
• Reservoir computing based on cellular automata (ReCA) in sequence learning
• Machine learning using cellular automata based feature expansion and reservoir computing
• Reservoir computing with computational matter
• Universal criticality in reservoir computing using asynchronous cellular automata

Cited in

(5)

• Machine learning using cellular automata based feature expansion and reservoir computing
• Reservoir computing based on cellular automata (ReCA) in sequence learning
• Universal criticality in reservoir computing using asynchronous cellular automata
• Reservoir Computing with Complex Cellular Automata
• Symbolic computation using cellular automata-based hyperdimensional computing

This page was built for publication: Reservoir computing using nonuniform binary cellular automata

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5126836)