Some stability properties of dynamic neural networks
Authors:
- 1 February 2001
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 48 (2) , 256-259
Abstract
In this paper, the passivity-based approach is used to derive a tuning algorithm for a class of dynamic neural networks. Several stability properties, such as passivity, asymptotic stability, input-to-state stability and bounded input-bounded output stability, are guaranteed in certain senses.Keywords
This publication has 18 references indexed in Scilit:
- Input-to-state stability (ISS) analysis for dynamic neural networks2002
- Nonlinear adaptive trajectory tracking using dynamic neural networksIEEE Transactions on Neural Networks, 1999
- Lur'e systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativityIEEE Transactions on Automatic Control, 1999
- Indirect adaptive control via paralleldynamic neural networksIEE Proceedings - Control Theory and Applications, 1999
- Constructive Nonlinear Control1997
- Multilayer neural-net robot controller with guaranteed tracking performanceIEEE Transactions on Neural Networks, 1996
- On characterizations of the input-to-state stability propertySystems & Control Letters, 1995
- High-order neural network structures for identification of dynamical systemsIEEE Transactions on Neural Networks, 1995
- Adaptive control of unknown plants using dynamical neural networksIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Stability conditions for nonlinear continuous neural networks with asymmetric connection weightsNeural Networks, 1992