Construction of Cellular Automata Using Machine Learning Models
( Pp. 13-22)

The paper is devoted to the development and study of cellular automata approximation methods using machine learning models. Cellular automata are models used to study the dynamics of complex systems based on simple interaction rules. In recent years, machine learning models have become powerful tools in the field of data processing. The paper examines approaches to predicting cellular automata rules using machine learning models, considers their advantages and limitations, and proposes metrics for assessing the quality of cellular automata state predictions and the dependence of cellular automata state prediction on the number of cellular automata rule models entering the input for training. The study aims to understand how machine learning models can be used to analyze and model complex systems based on cellular automata, as well as possible prospects for the development of this approach. Based on the proposed metrics, a comparative analysis of the effectiveness of various machine learning models in predicting cellular automata rules is carried out.

Malmygin G.A., and Ershov N.M. Construction of cellular automata using machine learning models. Computational Nanotechnology. 12, 3 (2025), 13–22. DOI: 10.33693/2313-223X-2025-12-3-13-22. EDN: ATBKYL

Dorin A., Stepney S. What is artificial life today, and where should it go? Artificial Life. 2024. No. 30 (1). Pp. 1–15.
Bedau M.A., McCaskill J.S., Packard N.H. et al. Open problems in artificial life. Artificial Life. 2000. No. 6. Pp. 363–376.
Von Neumann J., Burks A.W. Theory of self-reproducing automata. Urbana: University of Illinois Press, 1966.
Dittrich P. Artificial chemistry. In: Computational complexity: Theory, techniques, and applications. A.R. Meyers (ed.). Springer, 2012. Pp. 185–203.
Deutsch A., Dormann S. Cellular automaton modelling of biological pattern formation. Boston: Birkhauser, 2005.
Margolus N. Cellular automata machines: A new environment for modeling. MIT Press, 1987.
Achasova S., Bandman O., Markova V. et al. Parallel substitution algorithm. Theory and application. Singapore: World Scientific, 1994.
Kushner B. The constructive mathematics of A.A. Markov. Amer. Math. Monthly. 2006. No. 113 (6). Pp. 559–566.
Hopcroft J.E., Motwani R., Ullman J.D. Introduction to automata theory, languages, and computation second edition. Addison-Wesley, 2001.
Atkins P., Julio P. The rates of chemical reactions. Atkins' Physical chemistry. 8th ed. W.H. Freeman (ed.). 2006.
Aach M., G bbert J.H., Jitsev J. Generalization over different cellular automata rules learned by a deep feed-forward neural network. arXiv. Preprint arXiv:2103.14886. 2021.
Malmygin G.A., Ershov N.M. Chemical reactions modeling using cellular automata. System Analysis in Science and Education. 2023. No. 3. Pp. 1 13.
Von Neumann J., Burks A.W. Theory of self-reproducing automata. Urbana: University of Illinois Press, 1966.
Wolfram S. A new kind of science. Wolfram Media, 2002.
Toffoli T., Margolus N. Cellular automata machines: A new environment for modeling. MIT Press, 1987
Delashmit W.H. et al. Recent developments in multilayer perceptron neural networks. In: Proceedings of the seventh annual Memphis area engineering and science conference, MAESC. 2005. Vol. 7. P. 33.
Peterson L.E. K-nearest neighbor. Scholarpedia. 2009. Vol. 4. No. 2. P. 1883.
Ying L.U. et al. Decision tree methods: Applications for classification and prediction. Shanghai Archives of Psychiatry. 2015. Vol. 27. No. 2. P. 130.
Rigatti S.J. Random forest. Journal of Insurance Medicine. 2017. Vol. 47. No. 1. Pp. 31 39.
Game of life cellular automata. A. Adamatzky (ed.). London. Springer, 2010. Vol. 1. P. 168.
White S.H., Del Rey A.M., S nchez G.R. Modeling epidemics using cellular automata. Applied Mathematics and Computation. 2007. Vol. 186. No. 1. Pp. 193 202.

cellular automata, neural networks, nearest neighbors method, decision trees, random forest method.