Equilibrium characterization of dynamical neural networks for synthesis of associative memories

Several new results concerning the characterization of the equilibrium conditions of a continuous-time dynamical neural network model and a systematic procedure for synthesizing associative memory networks with nonsymmetrical interconnection matrices are presented. The equilibrium characterization focuses on the exponential stability, and instability properties of the network equilibria and on equilibrium confinement, namely, ensuring the uniqueness of an equilibrium in a specific region of the state space. The present synthesis procedure not only expands the scope of memory storage by removing the restrictions of symmetry on the interconnection matrix but also constructively exploits the roles of the various network parameters in identifying a scheme for systematically tailoring these parameters