ReLiCADA -- Reservoir Computing using Linear Cellular Automata Design Algorithm

TL;DR

This paper introduces a novel algorithm for designing Reservoir Computing models using linear Cellular Automata, optimizing rule selection and hyperparameters to improve accuracy and reduce training time for time series tasks.

Contribution

The paper presents a new rule selection algorithm for linear Cellular Automata in Reservoir Computing, significantly reducing training time and improving model accuracy.

Findings

Selected rules achieve low errors on benchmark datasets.

The approach reduces training and hyperparameter tuning time by orders of magnitude.

Models outperform state-of-the-art in accuracy and computational efficiency.

Abstract

In this paper, we present a novel algorithm to optimize the design of Reservoir Computing using Cellular Automata models for time series applications. Besides selecting the models' hyperparameters, the proposed algorithm particularly solves the open problem of linear Cellular Automaton rule selection. The selection method pre-selects only a few promising candidate rules out of an exponentially growing rule space. When applied to relevant benchmark datasets, the selected rules achieve low errors, with the best rules being among the top 5% of the overall rule space. The algorithm was developed based on mathematical analysis of linear Cellular Automaton properties and is backed by almost one million experiments, adding up to a computational runtime of nearly one year. Comparisons to other state-of-the-art time series models show that the proposed Reservoir Computing using Cellular Automata models have lower computational complexity, at the same time, achieve lower errors. Hence, our approach reduces the time needed for training and hyperparameter optimization by up to several orders of magnitude.