Reservoir Computing with Evolved Critical Neural Cellular Automata

TL;DR

This paper introduces a neural cellular automaton optimized for criticality using evolution strategies, demonstrating high performance in reservoir computing tasks like memory and image classification.

Contribution

It presents a novel method to evolve neural cellular automata to operate at criticality, enhancing reservoir computing capabilities.

Findings

Achieved perfect 5-bit memory task performance.

Surpassed elementary CA in image classification accuracy.

Exhibited robustness to extreme initial conditions.

Abstract

Criticality is a behavioral state in dynamical systems that is known to present the highest computation capabilities, i.e., information transmission, storage, and modification. Therefore, such systems are ideal candidates as a substrate for reservoir computing, a subfield in artificial intelligence. Our choice of a substrate is a cellular automaton (CA) governed by an artificial neural network, also known as neural cellular automaton (NCA). We apply evolution strategy to optimize the NCA to achieve criticality, demonstrated by power law distributions in structures called avalanches. With an evolved critical NCA, the substrate is tested for reservoir computing. Our evaluation of the substrate is performed with two benchmarks, 5-bit memory task and image classification of handwritten digits. The result of the 5-bit memory task achieved a perfect score and the system managed to remember all 5 bits. The result for the image classification task matched and sometimes surpassed the performance of the best elementary CA for this task. Moreover, the proposed critical NCA may operate as a self-organized critical system, due to its robustness to extreme initial conditions.