PASSIVITY OF A CLASS OF HOPFIELD NETWORKS - Application to Chaos Control

Adrian–Mihail Stoica, Isaac Yaesh

Abstract

The paper presents passivity conditions for a class of stochastic Hopfield neural networks with state–dependent noise and with Markovian jumps. The contributions are mainly based on the stability analysis of the considered class of stochastic neural networks using infinitesimal generators of appropriate stochastic Lyapunov–type functions. The derived passivity conditions are expressed in terms of the solutions of some specific systems of linear matrix inequalities. The theoretical results are illustrated by a simplified adaptive control problem for a dynamic system with chaotic behavior.

References

  1. Boyd, S., El-Ghaoui, L., Feron, L., and Balakrishnan, V. (1994). Linear matrix inequalities in system and control theory. SIAM.
  2. Cabrera, J., Bormann, R., Eurich, C., Ohira, T., and Milton, J. (2001). State-dependent noise and human balance control. Fluctuation and Noise Letters, 4:L107-L118.
  3. Cabrera, J. and Milton, J. (2004). Human stick balancing : Tuning levy flights to improve balance control. Physical Review Letters, 14:691-698.
  4. Dragan, V. and Morozan, T. (1999). Stability and robust stabilization to linear stochastic systems described by differential equations with markovian jumping and multiplicative white noise. The Institute of Mathematics of the Romanian Academy, Preprint 17/1999.
  5. Dragan, V. and Morozan, T. (2004). The linear quadratic optimiziation problems for a class of linear stochastic systems with multiplicative white noise and markovian jumping. IEEE Transactions on Automat. Contr., 49:665-675.
  6. Fen, X., Loparo, K., Ji, Y., and Chizeck, H. (1992). Stochastic stability properties of jump linear systems. IEEE Transactions on Automat. Contr., 37:38-53.
  7. Hu, S., Liao, X., and Mao, X. (2003). Stochastic hopfield neural networks. Journal of Physics A:Mathematical and General, 36:1-15.
  8. Stoica, A. and Yaesh, I. (2006). Delayed hopfield networks with multiplicative noise and jump markov parameters. In MTNS 2006, Kyoto.
  9. X. Liao, G. C. and Sanchez, E. (2002). Lmi based approach to asymptotically stability analysis of delayed neural networks. IEEE Transactions on Circuits and Systems E: Fundamental Theory and Applications, 49:1033- 1039.
  10. Yaesh, I. and Shaked, U. (2005). Stochastic passivity and its application in adaptive control. In CDC 2005, Kyoto.
Download


Paper Citation


in Harvard Style

Stoica A. and Yaesh I. (2008). PASSIVITY OF A CLASS OF HOPFIELD NETWORKS - Application to Chaos Control . In Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 978-989-8111-32-6, pages 84-89. DOI: 10.5220/0001478500840089


in Bibtex Style

@conference{icinco08,
author={Adrian–Mihail Stoica and Isaac Yaesh},
title={PASSIVITY OF A CLASS OF HOPFIELD NETWORKS - Application to Chaos Control},
booktitle={Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2008},
pages={84-89},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001478500840089},
isbn={978-989-8111-32-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - PASSIVITY OF A CLASS OF HOPFIELD NETWORKS - Application to Chaos Control
SN - 978-989-8111-32-6
AU - Stoica A.
AU - Yaesh I.
PY - 2008
SP - 84
EP - 89
DO - 10.5220/0001478500840089