On a time-variant associative memory

This paper proposes a novel time-variant associative memory. It guarantees the storing of any independent desired memory set and includes time-variant self-feedback W/sub ii/. If W/sub ii/ is a negative constant then the net has few spurious memories but has many oscillatory states, and if W/sub ii/ is a positive constant then the net does not oscillate but has many spurious memories. Then letting W/sub ii/ be time-variant, each merit is summed up, i.e. many spurious memories can escape from themselves to desired memories.

[1]  Shigetoshi Nara,et al.  Memory search using complex dynamics in a recurrent neural network model , 1993, Neural Networks.

[2]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Waugh,et al.  Associative memory in an analog iterated-map neural network. , 1990, Physical review. A, Atomic, molecular, and optical physics.