Complex-valued multistate neural associative memory
IEEE Transactions on Neural Networks
Models of self-correlation type complex-valued associative memories and their dynamics
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Hi-index | 0.00 |
This paper presents a model of self-correlation type associative memories using complex-valued continuous neural networks and studies its qualitative behaviors theoretically. The proposed model is an extension of the conventional real-valued associative memories of selfcorrelation type. We investigate the structures and asymptotic behaviors of solution orbits near each memory pattern. We also discuss a recalling condition of each memory pattern, that is, a condition which assures that each memory pattern is correctly recalled.