Chaotic Complex-Valued Bidirectional Associative Memory

In this paper, we propose a chaotic complex-valued bidirectional associative memory (CCBAM) which can realize one-to-many associations of multi-valued patterns. The proposed model is based on the bidirectional associative memory, and is composed of complex-valued neurons and chaotic complex-valued neurons. In the proposed model, associations of multi-valued patterns are realized by using complex-valued neurons, and one-to-many associations are realized by using chaotic complex-valued neurons. We carried out a series of computer experiments and confirmed that the proposed model can realize one-to-many associations of multi-valued patterns.