In this paper, we present new conditions ensuring existence, uniqueness, and Global Asymptotic Stability (GAS) of the equilibrium point for a large class of neural networks, The results are applicable to both symmetric and nonsymmetric interconnection matrices and allow for the consideration of all continuous nondecreasing neuron activation functions, Such functions may be unbounded (but not necessarily surjective), may have infinite intervals with zero slope as in a piece-wise-linear model, or both, The conditions on GAS rely on the concept of Lyapunov Diagonally Stable (or Lyapunov Diagonally Semi-Stable) matrices and are proved by employing a class of Lyapunov functions of the generalized Lur'e-Postnikov type, Several classes of interconnection matrices of applicative interest are shown to satisfy our conditions for GAS, In particular, the results are applied to analyze GAS for the class of neural circuits introduced in [10] for solving linear and quadratic programming problems. In this application, the principal result here obtained is that the networks in [10] are GAS also when the constraint amplifiers are dynamical, as it happens in any practical implementation.
New conditions for global stability of neural networks with application to linear and quadratic programming problems / M. Forti; A. Tesi. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I. FUNDAMENTAL THEORY AND APPLICATIONS. - ISSN 1057-7122. - STAMPA. - 42:(1995), pp. 354-366. [10.1109/81.401145]
New conditions for global stability of neural networks with application to linear and quadratic programming problems
TESI, ALBERTO
1995
Abstract
In this paper, we present new conditions ensuring existence, uniqueness, and Global Asymptotic Stability (GAS) of the equilibrium point for a large class of neural networks, The results are applicable to both symmetric and nonsymmetric interconnection matrices and allow for the consideration of all continuous nondecreasing neuron activation functions, Such functions may be unbounded (but not necessarily surjective), may have infinite intervals with zero slope as in a piece-wise-linear model, or both, The conditions on GAS rely on the concept of Lyapunov Diagonally Stable (or Lyapunov Diagonally Semi-Stable) matrices and are proved by employing a class of Lyapunov functions of the generalized Lur'e-Postnikov type, Several classes of interconnection matrices of applicative interest are shown to satisfy our conditions for GAS, In particular, the results are applied to analyze GAS for the class of neural circuits introduced in [10] for solving linear and quadratic programming problems. In this application, the principal result here obtained is that the networks in [10] are GAS also when the constraint amplifiers are dynamical, as it happens in any practical implementation.File | Dimensione | Formato | |
---|---|---|---|
Forti-Tesi-1995.htm
Accesso chiuso
Tipologia:
Altro
Licenza:
Tutti i diritti riservati
Dimensione
1.02 kB
Formato
HTML
|
1.02 kB | HTML | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.