Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
DIBLÍK, J. SHATYRKO, A. KHUSAINOV, D. OLEKSII, B. BAŠTINEC, J.
Originální název
Construction and Optimization of Stability Conditions of Learning Processes in Mathematical Models of Neurodynamics
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
This article is devoted to dynamic processes in the field of artificial intelligence, namely in the tasks of neurodynamics: the field of knowledge in which neural networks are considered as nonlinear dynamical systems and focuses on the problem of stability. The systems under consideration share four common characteristics: a large number of nodes (neurons), nonlinearity, dissipativity, noise. The purpose of this work is to build to construct of asymptotic stability conditions for dynamic model of neuronet network, which is described in terms of ODE nonlinear systems. Main method of investigation is Lyapunov direct method. Authors show that solution of pointed problem can be reduced to the task of convex optimization. By realization on Python tools the algorithm of Nelder-Mead method, a number of numerical experiments were conducted to select the optimal parameters of the Lyapunov function.
Klíčová slova
Neuronet model; differential equation system; software; stability; Lyapunov function.
Autoři
DIBLÍK, J.; SHATYRKO, A.; KHUSAINOV, D.; OLEKSII, B.; BAŠTINEC, J.
Vydáno
2. 12. 2022
Nakladatel
CEUR-WS
ISSN
1613-0073
Periodikum
CEUR Workshop Proceedings
Stát
Spolková republika Německo
Strany od
1
Strany do
10
Strany počet
BibTex
@inproceedings{BUT187326, author="Andrej {Shatyrko} and Denys Ya. {Khusainov} and Bychkov {Oleksii} and Josef {Diblík} and Jaromír {Baštinec}", title="Construction and Optimization of Stability Conditions of Learning Processes in Mathematical Models of Neurodynamics", booktitle="9th International Scientific Conference {"}Information Technology and Implementation{"}", year="2022", journal="CEUR Workshop Proceedings", pages="1--10", publisher="CEUR-WS", issn="1613-0073" }