Assessing the robustness of critical behavior in stochastic cellular automata

TL;DR

This paper investigates the robustness of critical behavior in stochastic cellular automata under noise perturbations, demonstrating that such systems can maintain criticality up to a certain noise level, with implications for brain-inspired AI.

Contribution

It systematically analyzes how stochastic cellular automata at criticality respond to probabilistic perturbations, revealing their robustness and potential for AI applications.

Findings

Critical stochastic CA remains in critical regime under moderate noise

Power-law fitting metrics confirm robustness of critical behavior

Implications for designing noise-tolerant brain-inspired AI systems

Abstract

There is evidence that biological systems, such as the brain, work at a critical regime robust to noise, and are therefore able to remain in it under perturbations. In this work, we address the question of robustness of critical systems to noise. In particular, we investigate the robustness of stochastic cellular automata (CAs) at criticality. A stochastic CA is one of the simplest stochastic models showing criticality. The transition state of stochastic CA is defined through a set of probabilities. We systematically perturb the probabilities of an optimal stochastic CA known to produce critical behavior, and we report that such a CA is able to remain in a critical regime up to a certain degree of noise. We present the results using error metrics of the resulting power-law fitting, such as Kolmogorov-Smirnov statistic and Kullback-Leibler divergence. We discuss the implication of our results in regards to future realization of brain-inspired artificial intelligence systems.