KECHAR, YoucefMerabet, Brahim Encadreur2025-09-142025-09-142025https://dspace.univ-ghardaia.edu.dz/xmlui/handle/123456789/9790Spécialité : Analyse Fonctionnelle et ApplicationsIn this memoir, we deal with the problem of analyzing the global exponential stability of a class of recurrent neural networks (RNNs) with discrete and distributed mixed delays, let us consider the existence and uniqueness of équilibriste points. use a new Lyapunov-krasvsckii functional and develop a linear matrix inequality (LMI) approach to make RNNs exponentially global stable.:Generalized recurrent neural networks; Discrete and distributed delays; Lyapunov- Krasovskii functional; Global exponential stability; Global asymptotic stability.:Réseaux de neurones récurrents généralisés ; Retards discrets et distribués ;fonc- tionnelle Lyapunov-Krasovskii ; Stabilité exponentielle globale ; Stabilité asymptotique globale.Thesis