loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Thibaud Comelli 1 ; Frédéric Pinel 2 and Pascal Bouvry 2

Affiliations: 1 Polytech Lille, University of Lille, France ; 2 Faculty of Science, Technology and Medicine, University of Luxembourg, Luxembourg

Keyword(s): Cellular Automata, Cellular Automata Classification, Convolutional Neural Network.

Abstract: Elementary cellular automata (ECA) are simple dynamic systems which display complex behaviour from simple local interactions. The complex behaviour is apparent in the two-dimensional temporal evolution of a cellular automata, which can be viewed as an image composed of black and white pixels. The visual patterns within these images inspired several ECA classifications, aimed at matching the automatas’ properties to observed patterns, visual or statistical. In this paper, we quantitatively compare 11 ECA classifications. In contrast to the a priori logic behind a classification, we propose an a posteriori evaluation of a classification. The evaluation employs a convolutional neural network, trained to classify each ECA to its assigned class in a classification. The prediction accuracy indicates how well the convolutional neural network is able to learn the underlying classification logic, and reflects how well this classification logic clusters patterns in the temporal evolution. Resu lts show different prediction accuracy (yet all above 85%), three classifications are very well captured by our simple convolutional neural network (accuracy above 99%), although trained on a small extract from the temporal evolution, and with little observations (100 per ECA, evolving 513 cells). In addition, we explain an unreported ”pathological” behaviour in two ECAs. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.21.46.24

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Comelli, T.; Pinel, F. and Bouvry, P. (2021). Comparing Elementary Cellular Automata Classifications with a Convolutional Neural Network. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-484-8; ISSN 2184-433X, SciTePress, pages 467-474. DOI: 10.5220/0010160004670474

@conference{icaart21,
author={Thibaud Comelli. and Frédéric Pinel. and Pascal Bouvry.},
title={Comparing Elementary Cellular Automata Classifications with a Convolutional Neural Network},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2021},
pages={467-474},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010160004670474},
isbn={978-989-758-484-8},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Comparing Elementary Cellular Automata Classifications with a Convolutional Neural Network
SN - 978-989-758-484-8
IS - 2184-433X
AU - Comelli, T.
AU - Pinel, F.
AU - Bouvry, P.
PY - 2021
SP - 467
EP - 474
DO - 10.5220/0010160004670474
PB - SciTePress