Analysis and synthesis of neural networks with lower block triangular interconnecting structure

A qualitative analysis of Hopfield-type neural network models with lower block triangular interconnecting structure is conducted. The approach views such networks as interconnected systems, and the results are phrased in terms of the qualitative properties of the subsystems of the networks and in terms of the properties of the interconnecting structure of networks. The results address the stability properties of equilibrium points and estimates of trajectory properties (e.g. rates of convergence of solutions to asymptotically stable equilibria). A design procedure for neural networks which are endowed with an interconnecting structure in block lower triangular form is presented