MODELING AND QUALITATIVE-ANALYSIS OF CONTINUOUS-TIME NEURAL NETWORKS UNDER PURE STRUCTURAL VARIATIONS

Authors
GRUJIC LT MICHEL AN
Citation
Lt. Grujic et An. Michel, MODELING AND QUALITATIVE-ANALYSIS OF CONTINUOUS-TIME NEURAL NETWORKS UNDER PURE STRUCTURAL VARIATIONS, Mathematics and computers in simulation, 40(5-6), 1996, pp. 523-533
Citations number
13
Categorie Soggetti
Computer Sciences",Mathematics,"Computer Science Interdisciplinary Applications","Computer Science Software Graphycs Programming
Journal title
Mathematics and computers in simulation → ACNP
ISSN journal
03784754
Volume
40
Issue
5-6
Year of publication
1996
Pages
523 - 533
Database
ISI
SICI code
0378-4754(1996)40:5-6<523:MAQOCN>2.0.ZU;2-0
Abstract
A qualitative analysis is developed for continuous-time neural network s subjected to random pure structural variations. Simple algebraic con ditions are established for both structural exponential stability of x = 0 of the neural network and for estimates of its domain of attracti on. Bounds on motions of the neural network in a forced regime are pro vided. They do not require any information about its actual structure, which can be completely unknown and may vary unpredictably.