Knowledge processing system using multidirectional associative memory

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.

[1]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[2]  Masao Nakagawa,et al.  Episodic associative memory , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[3]  H. Eichenbaum,et al.  Memory, amnesia, and the hippocampal system , 1993 .

[4]  Masao Nakagawa,et al.  Quick learning for bidirectional associative memory , 1994 .

[5]  Rodger E. Ziemer,et al.  Digital Communications and Spread Spectrum Systems , 1985 .

[6]  Heekuck Oh,et al.  Adaptation of the relaxation method for learning in bidirectional associative memory , 1994, IEEE Trans. Neural Networks.

[7]  Masafumi Hagiwara.  Multidirectional associative memory , 1990 .

[8]  Gillian Cohen,et al.  MEMORY A COGNITIVE APPROACH , 1986 .