Title :
Multimodule associative memory for many-to-many associations
Author :
Hattori, Motonobu ; Hagiwara, Masafumi
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
A multimodule associative memory for many-to-many associations (MMA)2 is proposed. The features of the proposed (MMA)2 are: 1) it can memorize and recall not only many-to-many associations but also the context and union associations; 2) it can guarantee the recall of all training data; and 3) it has high storage capacity
Keywords :
associative processing; content-addressable storage; learning (artificial intelligence); neural nets; pattern recognition; context association; many-to-many associations; multimodule associative memory; quick learning algorithm; storage capacity; union association; Artificial intelligence; Associative memory; Biological neural networks; Hebbian theory; Humans; Training data;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488886
