TY - GEN
T1 - On the memorization accuracy of autoassociative memory models
AU - Masuda, Kazuaki
AU - Aiyoshi, Eitaro
PY - 2011/1/1
Y1 - 2011/1/1
N2 - An autoassociative memory which is modeled as the standard recurrent neural network (N.N.) is capable of storing multiple patterns and subsequently recalling one of them in response to an input signal. However, we found in our recent trials that it can't always recall correct patterns accurately. In this paper, we demonstrate such phenomena by numerical examples and identify the cause of memorization errors. We also propose an immediate solution to memorize correct patterns without fail by storing extra patterns at the same time.
AB - An autoassociative memory which is modeled as the standard recurrent neural network (N.N.) is capable of storing multiple patterns and subsequently recalling one of them in response to an input signal. However, we found in our recent trials that it can't always recall correct patterns accurately. In this paper, we demonstrate such phenomena by numerical examples and identify the cause of memorization errors. We also propose an immediate solution to memorize correct patterns without fail by storing extra patterns at the same time.
KW - autoassociative memory
KW - local optimality
KW - nonlinear dynamical system
KW - recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=81255147443&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=81255147443&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:81255147443
SN - 9784907764395
T3 - Proceedings of the SICE Annual Conference
SP - 530
EP - 536
BT - SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts
PB - Society of Instrument and Control Engineers (SICE)
T2 - 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
Y2 - 13 September 2011 through 18 September 2011
ER -