Preview

Modeling and Analysis of Information Systems

Advanced search

On the Equilibrium State Stability of a Neural Network Model

https://doi.org/10.18255/1818-1015-2014-3-55-61

Abstract

In the paper, a neural network model based on three McCulloch–Pitts adder neurons is considered. Previously, the features of the model dynamics were numerically analyzed and the stability of various dynamic modes of the network with small changes of the current state was studied, including the detection of parameters specific for the chaotic system dynamics. In the paper, the stability problem of the neural network equilibrium states (steady operating mode) is considered for different values of feedback synaptic weight coefficients. An analytic proof of the zero equilibrium state instability for the corresponding dynamic system for all parameter values of the neural network is presented as the main result of the article.

About the Author

Y. V. Bogomolov
P.G. Demidov Yaroslavl State University
Russian Federation
старший преподаватель кафедры дискретного анализа, Sovetskaya str., 14, Yaroslavl, 150000, Russia


References

1. Wasserman P.D. Neural Computing, theory and Practice. Van Nostrand Reinhold, New York, 1989.

2. Богомолов Ю. В. О хаотическом поведении одной модели нейронной сети // Моделирование и анализ информационных систем. 2003. Т. 10, № 2. С. 35–40. [Bogomolov Yu. V. O khaoticheskom povedenii odnoy modeli neyronnoy seti // Modelirovanie i analiz informatsionnykh sistem. 2003. T. 10, № 2. S. 35–40 (in Russian)].

3. Radu Dogaru, A.T. Murgan, Daniel Ioan. Robust Oscillations and Bifurcations in Cellular Neural Networks // Proceedings of IEEE Int. Workshop on Cellular Neural Networks and Their Applications (CNNA’94). Rome, 1994. P. 297–302.

4. Джури Э. Инноры и устойчивость динамических систем. М.: Наука, 1979. 304 с. (Jury E.I. Innors and Stability of Dynamic Systems. New York: Wiley, 1974.)


Review

For citations:


Bogomolov Y.V. On the Equilibrium State Stability of a Neural Network Model. Modeling and Analysis of Information Systems. 2014;21(3):55-61. (In Russ.) https://doi.org/10.18255/1818-1015-2014-3-55-61

Views: 906


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 1818-1015 (Print)
ISSN 2313-5417 (Online)