Neural Network-based Method for Identifying Nominal Emergence in a Discrete System
( Pp. 114-124)
More about authors
Borovik Konstantin Ya.
postgraduate student, Department of Information Systems and Telecommunications
Bauman Moscow State Technical University
Moscow, Russian Federation Alfimtsev Alexander N. Dr. Sci. (Eng.), Professor; Head, Department of Information Systems and Telecommunications; Bauman Moscow State Technical University; Moscow, Russian Federation
Bauman Moscow State Technical University
Moscow, Russian Federation Alfimtsev Alexander N. Dr. Sci. (Eng.), Professor; Head, Department of Information Systems and Telecommunications; Bauman Moscow State Technical University; Moscow, Russian Federation
Abstract:
This paper investigates the possibility of detecting the effect of nominal emergence in a complex system using Conway’s Game of Life cellular automaton as a case study. The theoretical foundations of emergence are outlined, various types of emergence are considered, and a method for identifying nominal emergence in a complex system is proposed. To detect nominal emergence, artificial neural network architectures are designed to map the system from the micro level to the macro level. A decrease in the accuracy of predicting macro-level dynamics compared to the micro level is demonstrated, which indicates the presence of nominal emergence in the system.
How to Cite:
Borovik K.Ya. and Alfimtsev A.N. Neural network-based method for identifying nominal emergence in a discrete system. Computational Nanotechnology. 13, 1 (2026), 114–124. DOI: 10.33693/2313-223X-2026-13-1-114-124. EDN: MQGZDJ
Reference list:
Antsiperov V.E. Generative model of autoencoders, self-learning on images represented by sample points. Automation and Remote Control. 2022. No. 12. Pp. 108–140. (In Rus.)
Bagaev I.I. Analysis of the concepts of neural network and convolutional neural network, training of a convolutional neural network using the TensorFlow module. Software of Systems in the Industrial and Social Spheres. 2020. Vol. 8. No. 1. Pp. 15–22. (In Rus.)
Downey A.B. Complexity science with Python. D.A. Belikov (transl. from English). Moscow: DMK Press, 2019. 160 p. ISBN: 978-5-97060-712-1.
Bedau M.A. Weak emergence. Philosophical Perspectives. 1997. Vol. 11. Pp. 375–399.
Hoel E.P., Albantakis L., Tononi G. Quantifying causal emergence shows that macro can beat micro. Proceedings of the National Academy of Sciences. 2013. Vol. 110. No. 49. Pp. 19790–19795.
Mediano P.A.M., Seth A.K., Barrett A.B. Measuring integrated information: Comparison of candidate measures in theory and simulation. Entropy. 2019. Vol. 21. No. 1. Art. 17.
Santamaría-Bonfil G., Gershenson C., Fernández N. A Package for measuring emergence, self-organization, and complexity based on Shannon entropy. Frontiers in Robotics and AI. 2017. Vol. 4. Art. 10. DOI: 10.3389/frobt.2017.00010. EDN: PKPVSK.
Seth A.K. Measuring autonomy and emergence via Granger causality. Artificial Life. 2010. Vol. 16. No. 2. Pp. 179–196. DOI: 10.1162/artl.2010.16.2.16204. EDN: NYTITV.
Springer J.M., Kenyon G.T. It’s hard for neural networks to learn the game of life. In: International Joint Conference on Neural Networks (IJCNN). IEEE, 2021. Pp. 1–8.
Systems analysis approach for complex global challenges. P. Mensah et al. (eds.). Springer, 2018. EDN: YJQCLZ.
Thoren H., Gerlee P. Weak emergence and complexity. MIT Press, 2010. 250 p.
Yang M. et al. Finding emergence in data by maximizing effective information. National Science Review. 2025. Vol. 12. No. 1. DOI: 10.1093/nsr/nwae279. EDN: RQKAGB.
Yuan B. et al. Emergence and causality in complex systems: A survey of causal emergence and related quantitative studies. Entropy. 2024. Vol. 26. No. 2. Art. 108. DOI: 10.3390/e26020108. EDN: MTXAEF.
Zhang J., Liu K. Neural information squeezer for causal emergence. Entropy. 2022. Vol. 25. No. 1. Art. 26. DOI: 10.3390/e25010026. EDN: UZDQKR.
Zhu J., Jang-Jaccard J., Watters P.A. Multi-loss siamese neural network with batch normalization layer for malware detection. IEEE Access. 2020. Vol. 8. Pp. 171542–171550. DOI: 10.1109/access.2020.3024991. EDN: ZEOCBL.
Bagaev I.I. Analysis of the concepts of neural network and convolutional neural network, training of a convolutional neural network using the TensorFlow module. Software of Systems in the Industrial and Social Spheres. 2020. Vol. 8. No. 1. Pp. 15–22. (In Rus.)
Downey A.B. Complexity science with Python. D.A. Belikov (transl. from English). Moscow: DMK Press, 2019. 160 p. ISBN: 978-5-97060-712-1.
Bedau M.A. Weak emergence. Philosophical Perspectives. 1997. Vol. 11. Pp. 375–399.
Hoel E.P., Albantakis L., Tononi G. Quantifying causal emergence shows that macro can beat micro. Proceedings of the National Academy of Sciences. 2013. Vol. 110. No. 49. Pp. 19790–19795.
Mediano P.A.M., Seth A.K., Barrett A.B. Measuring integrated information: Comparison of candidate measures in theory and simulation. Entropy. 2019. Vol. 21. No. 1. Art. 17.
Santamaría-Bonfil G., Gershenson C., Fernández N. A Package for measuring emergence, self-organization, and complexity based on Shannon entropy. Frontiers in Robotics and AI. 2017. Vol. 4. Art. 10. DOI: 10.3389/frobt.2017.00010. EDN: PKPVSK.
Seth A.K. Measuring autonomy and emergence via Granger causality. Artificial Life. 2010. Vol. 16. No. 2. Pp. 179–196. DOI: 10.1162/artl.2010.16.2.16204. EDN: NYTITV.
Springer J.M., Kenyon G.T. It’s hard for neural networks to learn the game of life. In: International Joint Conference on Neural Networks (IJCNN). IEEE, 2021. Pp. 1–8.
Systems analysis approach for complex global challenges. P. Mensah et al. (eds.). Springer, 2018. EDN: YJQCLZ.
Thoren H., Gerlee P. Weak emergence and complexity. MIT Press, 2010. 250 p.
Yang M. et al. Finding emergence in data by maximizing effective information. National Science Review. 2025. Vol. 12. No. 1. DOI: 10.1093/nsr/nwae279. EDN: RQKAGB.
Yuan B. et al. Emergence and causality in complex systems: A survey of causal emergence and related quantitative studies. Entropy. 2024. Vol. 26. No. 2. Art. 108. DOI: 10.3390/e26020108. EDN: MTXAEF.
Zhang J., Liu K. Neural information squeezer for causal emergence. Entropy. 2022. Vol. 25. No. 1. Art. 26. DOI: 10.3390/e25010026. EDN: UZDQKR.
Zhu J., Jang-Jaccard J., Watters P.A. Multi-loss siamese neural network with batch normalization layer for malware detection. IEEE Access. 2020. Vol. 8. Pp. 171542–171550. DOI: 10.1109/access.2020.3024991. EDN: ZEOCBL.
Keywords:
emergence, complex systems, neural networks, cellular automata, autoencoder.
