The Use of the Concept of “Typical Process” in Machine Learning and Artificial Intelligence Systems

Abstract

Typical processes are a fundamental invariant of many natural and artificial systems. The purpose of a typical process is to maintain homeostasis in the system. The system is in this case an information control network (ICN) with three generations of objects (the central network object acts as a teacher). Applying the concept of Typical Process and Semantic Anomaly in machine learning and artificial intelligence systems will avoid lots of computations and unpredictable results typical for systems with Deep Learning. While admittedly obvious, the concept of a typical process is difficult to formalize. It is proposed to use the mathematical apparatus of perturbation theory and fast-slow dynamic systems, slow variables are interpreted as semantic. An example of a machine learning problem is considered – the entry of a new object into a system reproducing an aggregated typical process. A possible tool for modeling changes in the typical process under the influence of the external environment is proposed to model using trajectories-ducks. To solve the problems of control of typical processes in automatic systems, the mathematical apparatus of Kurzhansky trajectory tubes and the predictor-corrector scheme, which in this situation has a certain physical meaning, are proposed. Artificial intelligence systems require modeling hierarchies of typical processes, which is a nontrivial mathematical problem.

Author Biographies

Villiam Karpovich Sarian, Federal State Unitary Enterprise Radio Research and Development Institute

Scientific Consultant, Academician of the Armenian National Academy of Sciences, Dr.Sci. (Engineering), Professor, Merited Worker of Communications of the Russian Federation

Alexander Alexandrovich Rusakov, MIREA – Russian Technological University

Professor of the Department of Higher Mathematics, Dr.Sci. (Pedagogy), Ph.D. (Phys.-Math.), Professor, Honorary Worker of Higher Education of the Russian Federation

Anatoly Petrovich Nazarenko, Federal State Unitary Enterprise Radio Research and Development Institute

Director of STC Satellite Monitoring and Communication, Ph.D. (Engineering), Professor

Dmitry Vladimirovich Dubnov, Moscow Technical University of Communications and Informatics

Associate Professor of the Department of Mathematical Analysis, Ph.D. (Phys.-Math.), Associate Professor

References

[1] Butenko V.V., Nazarenko A.P., Sarian V.K., Suschenko N.A., Lutokhin A.S. Problems that arise when introducing new technologies in the infocommunication community. Trudy NIIR. 2011; 1:12-19. Available at: https://elibrary.ru/item.asp?id=16335664 (accessed 02.08.2019). (In Russ.)
[2] Suggested Citation: Butenko V., Nazarenko A., Sarian V., Suschenko N. Issues affecting the evalution of the beneficial effect of new technologies and ways to solve these issues. In: 23rd European Regional Conference of the International Telecommunication Society, Vienna, Austria, 1-4 July 2012. ITS, Wien, 2012. Available at: https://www.econstor.eu/handle/10419/60398 (accessed 02.08.2019). (In Eng.)
[3] Y.2239: Requirements for Information Control Networks and related application. Series Y: Global Information Infrastructure, Internet Protocol Aspects and Next-generation Networks Next Generation Networks – Service Aspects: Service Capabilities and Service Architecture, ITU-T, 2015. Available at: https://www.itu.int/rec/T-REC-Y.2239-201602-I/en (accessed 02.08.2019). (In Eng.)
[4] Sarian V.K. A new way of structuring data transmission networks. Trudy NIIR. 2001; 41-49. (In Russ.)
[5] Sarian V.K. Model of information interaction of objects in data transmission networks. Trudy NIIR. 2001; 50-55. (In Russ.)
[6] Sarian V., Nazarenko A., Levashov V.K., Salomatina E.V. Influence of the development of infocommunication technologies (ICT) on security in the economic and social sphere and the sphere of public process management. In: Analysis, modeling, management, development of socio-economic systems. Proceedings of the XI International School-Symposium AMUR-2017, Publishing House of IP Kornienko A.A., 2017, pp. 361-364. Available at: https://elibrary.ru/item.asp?id=32411752 (accessed 02.08.2019). (In Russ.)
[7] Nazarenko A., Sarian V. Internet of Things Technology - A Powerful Catalyst Functioning Single Digital Space. Trudy NIIR. 2016; 4:16-20. Available at: https://elibrary.ru/item.asp?id=29334919 (accessed 02.08.2019). (In Russ., abstract in Eng.)
[8] Nazarenko A., Sarian V. Using the Internet of Things to Radically Reduce the Risk of Losses in Emergencies. In: Information Society Technologies. Proceedings of the XIII International Industrial Scientific and Technical Conference. Media Publisher, Moscow, 2019, vol. 2, pp. 66-68. Available at: https://elibrary.ru/item.asp?id=39228401 (accessed 02.08.2019). (In Russ.)
[9] Sarian V., Nazarenko A. Draft Recommendation Y.IoT-GP-Reqts “Requirements for an IoT enabled network to support applications for global processes of the Earth” - output of Q2/20 meeting. Geneva, 25 July-5 August 2016. ITU-R, Y3777, 2016. (In Eng.)
[10] Nazarenko A.P., Sarian V.K., Lutokhin A.S. Using of Flying Internet of Things Before, During and after Critical Stage of a Disaster. Electrosvyaz. 2015; 7:12-15. Available at: https://elibrary.ru/item.asp?id=23805308 (accessed 02.08.2019). (In Russ., abstract in Eng.)
[11] Sarian V.K., Rusakov A.A., Dubnov D.V. Typical processes in physics and mathematics. In: Mozharova T.N. (ed). Proceedings of the V Scientific-practical Conference with International Participation "Modern problems of physical and mathematical sciences" (SPFMN- 2019). Oryol State University named after I.S. Turgenev, Oryol, 2019, pp. 236-238. Available at: https://phys-math.ru/_media/conf2019/spfmn-2019-sbornik.pdf (accessed 02.08.2019). (In Russ.)
[12] Sarian V.K., Dubnov D.V. Interference immunity of typical information processes in mass data networks. Statement of a question. Trudy NIIR. 2007; 2:86-92. (In Russ.)
[13] Novickij V.V., Gol’dberg E.D., Urazova O.I. Patofiziologiya [Pathophysiology]. 4 ed., GEOTAR- Media, Moscow, 2012. (In Russ.)
[14] Wassermen F.D. Neural Computing: Theory and Practice. Coriolis Group, First Edition, 1989. (In Eng.)
[15] Shishkova M.A. Examination of a system of differential equations with a small parameter in the highest derivatives. Doklady Akademii Nauk SSSR. 1973; 209(3):576-579. Available at: http://www.mathnet.ru/links/6e388c3b1b29e16296f39409af10a583/dan37550.pdf (accessed 02.08.2019). (In Russ., abstract in Eng.)
[16] Neystadt AI. Asymptotic study of the loss of stability of equilibrium during the slow passage of a pair of eigenvalues through the imaginary axis. Uspekhi Matematicheskikh Nauk = Russian Mathematical Surveys. 1985; 40(5):300-301. (In Russ.)
[17] Simonova T.V. Slow Integral Manifolds with a Change of Stability. Vestnik of Samara University. Natural Science Series. 2012; 6:49-57. Available at: https://elibrary.ru/item.asp?id=18248710 (accessed 02.08.2019). (In Russ., abstract in Eng.)
[18] Kurzhanski A. B., Vályi I. Ellipsoidal techniques for dynamic systems: The problems of control synthesis. Dynamics and Control. 1991; 1(4):357-378. (In Eng.) DOI: 10.1007/BF02169766
[19] Camacho E.F., Bordons Alba C. Model Predictive Control. Advanced Textbooks in Control and Signal Processing. Springer-Verlag London, 2007, 405 pp. (In Eng.) DOI: 10.1007/978-0-85729-398-5
[20] Nikolaou M. Model predictive controllers: A critical synthesis of theory and industrial needs. Advances in Chemical Engineering. 2000; 26:131-204. (In Eng.) DOI: 10.1016/S0065-2377(01)26003-7
[21] Lucia S., Finkler T., Engell S. Multi-stage nonlinear model predictive control applied to a semi-batch polymerization reactor under uncertainty. Journal of Process Control. 2013; 23(9):1306-1319. (In Eng.) DOI: 10.1016/j.jprocont.2013.08.008
[22] Golodova E.S., Shchepakina E.A Estimation of Delayed Loss of Stability in Differential Equations with Canards. Vestnik of Samara University. Natural Science Series. 2013; 3(104):12-24. Available at: https://elibrary.ru/item.asp?id=19062477 (accessed 02.08.2019). (In Russ., abstract in Eng.)
[23] Sobolev V.A., Shchepakina E.A. Duck trajectories in a problem of combustion theory. Differential Equations. 1996; 32(9):1177-1186. Available at: https://elibrary.ru/item.asp?id=13231308 (In Eng.)
[24] Troshkina E.V. Canard Curves in the Dynamic Model of Forest Insect Pests. Vestnik of Samara University. Natural Science Series. 2013; 9-2(110):215-220. Available at: https://elibrary.ru/item.asp?id=21288624 (accessed 02.08.2019). (In Russ., abstract in Eng.)
[25] Chekharin E.E. Big Data: Big Problems. Perspectives of Science and Education. 2016; 3(21):7-11. Available at: https://elibrary.ru/item.asp?id=26286829 (accessed 02.08.2019). (In Russ., abstract in Eng.)
Published
2019-09-30
How to Cite
SARIAN, Villiam Karpovich et al. The Use of the Concept of “Typical Process” in Machine Learning and Artificial Intelligence Systems. Modern Information Technologies and IT-Education, [S.l.], v. 15, n. 3, p. 693-701, sep. 2019. ISSN 2411-1473. Available at: <http://sitito.cs.msu.ru/index.php/SITITO/article/view/555>. Date accessed: 10 sep. 2025. doi: https://doi.org/10.25559/SITITO.15.201903.693-701.
Section
Cognitive information technologies in control systems