Chaotically Temporal Retrieval of Memory

A neural network with nonlinear delays to produce temporal retrieval of memory is presented. In this network, chaotic motion of the local fields provides a mechanism for the system to escape from one memory to another. It is proved by numerical investigations that the chaotic temporal process can explore the topological structure of the state space and the system has better efficiency of searching global minimum of the energy function than the Hopfield model. The characters of the system show that it may have great potential use in solving combinatorial optimization problems with its complex dynamics.