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
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.