Fuzzy data recall using polynomial bidirectional hetero-correlator

Author

Wang, Chua-Chin ; Tsai, Cheng-Fa

Author_Institution

Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan

Volume

2

fYear

1998

fDate

11-14 Oct 1998

Firstpage

1940

Abstract

A method of fuzzy data recall using polynomial bidirectional hetero-correlator is presented. This has a higher capacity for pattern pair storage than that of the conventional BAMs and fuzzy memories. A new energy function is defined. The polynomial bidirectional hetero-correlator (PBHC) takes advantage of fuzzy characteristics in evolution equations such that the signal-noise-ratio (SNR) is significantly increased. In this work, we prove the stability of fuzzy data recall using polynomial bidirectional hetero-correlator. The increase of SNR consequently enhances the capacity of the polynomial bidirectional hetero-correlator. The capacity of the fuzzy data recall using PBHC in the worst case is also estimated

Keywords

content-addressable storage; correlation methods; fuzzy neural nets; genetic algorithms; associative memory; energy function; evolution equations; fuzzy data recall; fuzzy memories; polynomial bidirectional hetero-correlator; signal-noise-ratio; storage capacity; Associative memory; Correlators; Equations; Fuzzy systems; Neural networks; Polynomials; Signal analysis; Stability; Sufficient conditions; Surface fitting;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on

Conference_Location

San Diego, CA

ISSN

1062-922X

Print_ISBN

0-7803-4778-1

Type

conf

DOI

10.1109/ICSMC.1998.728180

Filename

728180