Convolutional Neural Networks for Cellular Automata Classification

Silverman, E. (2019) Convolutional Neural Networks for Cellular Automata Classification. In: 2019 Conference on Artificial Life (ALIFE 2019), Newcastle, UK, 29 July - 02 Aug 2019, pp. 280-281. (doi:10.1162/isal_a_00175)

[img]
Preview
Text
187495.pdf - Published Version
Available under License Creative Commons Attribution.

147kB

Abstract

Wolfram famously developed a four-way classification of CA behaviour, with Class IV containing CAs that generate complex, localised structures. However, finding Class IV rules is far from straightforward, and can require extensive, time-consuming searches. This work presents a Convolutional Neural Network (CNN) that was trained on visual examples of CA behaviour, and learned to classify CA images with a high degree of accuracy. I propose that a refinement of this system could serve as a useful aid to CA research, automatically identifying possible candidates for Class IV behaviour and universality, and significantly reducing the time required to find interesting CA rules.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Silverman, Dr Eric
Authors: Silverman, E.
College/School:College of Medical Veterinary and Life Sciences > Institute of Health and Wellbeing > MRC/CSO SPHSU
Publisher:MIT Press
Published Online:15 July 2019
Copyright Holders:Copyright © 2019 Massachusetts Institute of Technology
Publisher Policy:Reproduced under a Creative Commons License
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
727661SPHSU Core Renewal: Complexity in Health Improvement Research ProgrammeLaurence MooreMedical Research Council (MRC)MC_UU_12017/14IHW - MRC/CSO SPHU
SPHSU14