Improvement of discrete-time cellular neural networks for associative memory using 2-dimensional discrete Walsh transform

Author

Kamio, Takeshi ; Asai, Hideki

Author_Institution

Fac. of Eng., Shizuoka Univ., Hamamatsu, Japan

fYear

1998

fDate

14-17 Apr 1998

Firstpage

416

Lastpage

421

Abstract

The conventional synthesis procedure of discrete-time cellular neural networks (DTCNNs) for associative memory may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this paper we propose the DTCNN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns which the conventional DTCNN fails to do

Keywords

cellular neural nets; content-addressable storage; transforms; 2-dimensional discrete Walsh transform; 2D discrete Walsh transforms; associative memory; discrete-time cellular neural networks; memory patterns; Associative memory; Asymptotic stability; Cellular neural networks; Discrete transforms; Discrete wavelet transforms; Electronic mail; Hardware; Integrated circuit interconnections; Network synthesis; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on

Conference_Location

London

Print_ISBN

0-7803-4867-2

Type

conf

DOI

10.1109/CNNA.1998.685420

Filename

685420