United Nations Educational, Scientific and Cultural Organization and International Atomic Energy Agency THE ABDUS SALAM INTERNATIONAL CENTRE FOR THEORETICAL PHYSICS DYNAMICAL BEHAVIOUR OF QUASI-PALINDROMIC NEURAL NETWORKS ITERATED WITH MEMORY
Paulin Melatagia Yonta, Abdus Salam · 2007
In this paper, we study memory iteration where the updating considers a longer history of each site and the set of interaction matrices is quasi-palindromic. For parallel and sequential iterations with memory, we define Lyapunov functional which permits us to characterize the periods behaviour and explicitly bounds the transient lengths of quasi-palindromic neural networks. For these networks, the dynamics are robust with respect to a class of small changes of the interactions matrices.