A novel continuous-time neural network for realizing associative memory

A novel neural network is proposed in this paper for realizing associative memory. The main advantage of the neural network is that each prototype pat tern is stored if and only if as an asymptotically stable equilibrium point . Furthermore, the basin of attraction of each desired memory pattern is di stributed reasonably (in the Hamming distance sense), and an equilibrium pa int that is not asymptotically stable is really the state that cannot be re cognized. The proposed network also has a high storage as well as the capab ility of learning and forgetting, and all its components can be implemented . The network considered is a very simple linear system with a projection o n a closed convex set spanned by the prototype patterns. The advanced perfo rmance of the proposed network is demonstrated by means of simulation of a numerical example.