TY - JOUR
T1 - Bidirectional associative memories
T2 - Different approaches
AU - Acevedo-Mosqueda, Maria Elena
AU - Yanez-Marquez, Cornelio
AU - Acevedo-Mosqueda, Marco Antonio
PY - 2013/2
Y1 - 2013/2
N2 - Bidirectional Associative Memories (BAM) are systems that allow to associate pairs of patterns. Once a memory has learned, patterns can be recalled in two directions. BAMs have many applications in pattern recognition and image processing. The aim of this survey is to present several models of BAM throughout time, since Kosko [1988] proposed the first model; followed by those works based on or inspired by it, trying to improve recall capacity; to some recent one-shot models-such as Morphological BAM and Alpha-Beta BAM-which are of particular interest, given their superior performance.
AB - Bidirectional Associative Memories (BAM) are systems that allow to associate pairs of patterns. Once a memory has learned, patterns can be recalled in two directions. BAMs have many applications in pattern recognition and image processing. The aim of this survey is to present several models of BAM throughout time, since Kosko [1988] proposed the first model; followed by those works based on or inspired by it, trying to improve recall capacity; to some recent one-shot models-such as Morphological BAM and Alpha-Beta BAM-which are of particular interest, given their superior performance.
KW - Bidirectional associative memories
KW - correct recall
KW - one-shot algorithms
UR - http://www.scopus.com/inward/record.url?scp=84875171081&partnerID=8YFLogxK
U2 - 10.1145/2431211.2431217
DO - 10.1145/2431211.2431217
M3 - Artículo de revisión
SN - 0360-0300
VL - 45
JO - ACM Computing Surveys
JF - ACM Computing Surveys
IS - 2
M1 - 18
ER -