Knowledge processing system using multidirectional associative memory

Author

Hattori, Motonobu ; Hagiwara, Masafumi

Author_Institution

Dept. of Electr. Eng., Keio Univ., Yokohama, Japan

Volume

3

fYear

1995

Firstpage

1304

Abstract

A knowledge processing system using multidirectional associative memory (KP-MAM) is proposed and simulated. The KP-MAM uses distributed knowledge representation and can represent knowledge stored in a form of semantic network. In order to realize knowledge processing system using distributed representation, the KP-MAM enables the following five functions: associations of three-tuple relation, characteristics inheritance, exception processing, many-to-many associations and high storage capacity. The proposed KP-MAM has the following features: (1) It can realize knowledge processing using distributed representation; (2) It is robust for noisy inputs; (3) It guarantees recall of all training data owing to a quick learning algorithm; (4) It has high storage capacity

Keywords

associative processing; content-addressable storage; exception handling; inheritance; learning (artificial intelligence); semantic networks; characteristics inheritance; distributed knowledge representation; exception processing; high storage capacity; knowledge processing system; many-to-many associations; multidirectional associative memory; quick learning algorithm; semantic network; Artificial intelligence; Artificial neural networks; Associative memory; Humans; Knowledge representation; Multi-layer neural network; Neural networks; Neurons; Robustness; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1995. Proceedings., IEEE International Conference on

Print_ISBN

0-7803-2768-3

Type

conf

DOI

10.1109/ICNN.1995.487345

Filename

487345