DocumentCode
303269
Title
Intersection learning for bidirectional associative memory
Author
Hattori, Motonobu ; Hagiwara, Masafumi
Author_Institution
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Volume
1
fYear
1996
fDate
3-6 Jun 1996
Firstpage
555
Abstract
We propose intersection learning for bidirectional associative memory (ILBAM). ILBAM is based on a novel relaxation method. A number of computer simulations show the effectiveness of ILBAM: (1) it can guarantee the recall of all training pairs; (2) it requires much lower weight renewal times than conventional methods; (3) it becomes more effective in the case where there are many training pairs needed to be stored; (4) it is insensitive to the correlation of training pairs; and (5) it contributes to the noise reduction effect of BAM
Keywords
content-addressable storage; bidirectional associative memory; intersection learning; noise reduction; relaxation method; training pair recalling; weight renewal times; Associative memory; Computer simulation; Hebbian theory; Humans; Magnesium compounds; Neurons; Noise reduction; Read-write memory; Relaxation methods; Reverberation;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1996., IEEE International Conference on
Conference_Location
Washington, DC
Print_ISBN
0-7803-3210-5
Type
conf
DOI
10.1109/ICNN.1996.548955
Filename
548955
Link To Document