Storing temporal sequences of patterns in neural networks
Dilip Krishnaswamy, Kishan G. Mehrotra, Chilukuri Krishna Mohan, Sanjay Ranka · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1993
This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The network were successfully implemented and the number of patterns that could be stored and recalled was approximately 12% of the size of the patterns in the network.