1 July 1992 Attentive multidirectional associative memory with application to pattern association
Author Affiliations +
An attentive multidirectional hetero-associative memory network (AMAM) is proposed. The convergence and encoding strategies of AMAM are described. This network enables multiple associations, but with certain associations embedding more attention. This model is inspired by speculation about how associative learning and storage might occur in the nervous system. AMAM has much better error correcting capability and memory capacity than the multidirectional associative memory. Examples are illustrated to show the advantages of this model. In addition, we demonstrate and compare its recall ability for pattern recognition.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Heng-Ming Tai, Heng-Ming Tai, } "Attentive multidirectional associative memory with application to pattern association", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140109; https://doi.org/10.1117/12.140109

Back to Top