TY - JOUR
T1 - A new model of BAM
T2 - Alpha-beta bidirectional associative memories
AU - Mosqueda, María Elena Acevedo
AU - Márquez, Cornelio Yáñez
AU - Yáñez, Itzamá López
PY - 2007/6
Y1 - 2007/6
N2 - Most models of Bidirectional associative memories intend to achieve that all trained pattern correspond to stable states; however, this has not been possible. Also, none of the former models has been able to recall all the trained patterns. In this work we introduce a new model of bidirectional associative memory which is not iterative and has no stability problems. It is based on the Alpha-Beta associative memories. This model allows, besides correct recall of noisy patterns, perfect recall of all trained patterns, with no ambiguity and no conditions. An example of fingerprint recognition is presented.
AB - Most models of Bidirectional associative memories intend to achieve that all trained pattern correspond to stable states; however, this has not been possible. Also, none of the former models has been able to recall all the trained patterns. In this work we introduce a new model of bidirectional associative memory which is not iterative and has no stability problems. It is based on the Alpha-Beta associative memories. This model allows, besides correct recall of noisy patterns, perfect recall of all trained patterns, with no ambiguity and no conditions. An example of fingerprint recognition is presented.
KW - Alpha-beta associative memories
KW - Bidirectional associative memories
KW - Perfect recall
UR - http://www.scopus.com/inward/record.url?scp=84871583700&partnerID=8YFLogxK
U2 - 10.4304/jcp.2.4.49-56
DO - 10.4304/jcp.2.4.49-56
M3 - Artículo
SN - 1796-203X
VL - 2
SP - 49
EP - 56
JO - Journal of Computers (Finland)
JF - Journal of Computers (Finland)
IS - 4
ER -