Reservoir Computing Using Non-Uniform Binary Cellular Automata
This work addresses improving reservoir computing efficiency for sequential data processing, but it is incremental as it builds on existing CA-based reservoir methods.
The paper investigates using non-uniform binary cellular automata (CA) as reservoirs in reservoir computing for sequential classification tasks, finding that certain CA rules and combinations improve performance, with larger reservoir sizes enhancing results.
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.