Title :
Chaotic bidirectional associative memory
Author :
Osana, Yuko ; Hattori, Motonobu ; Hagiwara, Masafumi
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
A chaotic bidirectional associative memory (CBAM) is proposed and simulated. It can deal with one-to-many associations such as {(A,a), (A,b), (A,c),···}. In the CBAM, in order to enable one-to-many associations, each training pair is memorized together with its own contextual information and chaotic neurons are employed in a part of the network corresponding to the contextual information. Since the chaotic neurons change their states by chaos, the one-to-many associations can be realized in the CBAM
Keywords :
chaos; content-addressable storage; learning (artificial intelligence); neural nets; chaotic bidirectional associative memory; chaotic neurons; contextual information; one-to-many associations; training pair; Associative memory; Biological neural networks; Chaos; Crosstalk; Damping; Equations; Human factors; Magnesium compounds; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549002
