A novel time-based neural coding for artificial neural networks with bifurcating recursive processing elements

This paper addresses a novel temporal coding technique, particularly adapted to artificial neural networks based on globally coupled maps, recursive processing elements, and model neurons with spiking dynamics defined by first order recursive maps. Such networks are used here to store quaternary patterns through programmed period-4 limit cycles. Important applications are the processing of spatio-temporal information, and the computation with non-fixed point attractors and compact neural architectures