Dynamic bidirectional associative memory using chaotic neurons

A dynamic bidirectional associative memory (DBAM) with chaotic neurons as nodes is proposed. A learning algorithm based on Pontryagin’s minimum principle makes the DBAM equivalent to any other BAM so far reported. The input selection mechanism gives the DBAM the additional ability of multiple memory access, which is based on the dynamics of the chaotic neuron. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999