Sparsely interconnected neural networks for associative memories applying discrete Walsh transform

被引：0

作者：

Kamio, T ^{[1
]}

Asai, H ^{[1
]}

机构：

[1] Shizuoka Univ, Fac Engn, Hamamatsu, Shizuoka 4328561, Japan

来源：

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES | 1999年 / E82A卷 / 03期

关键词：

sparsely interconnected neural network; associative memory; 2-dimensional discrete Walsh transform; isolated cells problem;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories 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 letter, we propose the DTSINN 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 DTSINN fails to do.

引用

页码：495 / 499

页数：5

共 8 条

[1] DISCRETE-TIME CELLULAR NEURAL NETWORKS FOR ASSOCIATIVE MEMORIES WITH LEARNING AND FORGETTING CAPABILITIES [J].

BRUCOLI, M ;

CARNIMEO, L ;

GRASSI, G .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1995, 42 (07) :396-399

[2]

KAMIO T, 1994, IEICE T FUND ELECTR, VE77A, P1882

[3]

KAMIO T, 1998, P IEEE INT WORKSH CE, P416

[4]

KAMIO T, 1997, P IEEE INSTR MEAS TE, P1210

[5]

KAWABATA H, 1995, IEICE T FUND ELECTR, V78, P1618

[6] SPARSELY INTERCONNECTED NEURAL NETWORKS FOR ASSOCIATIVE MEMORIES WITH APPLICATIONS TO CELLULAR NEURAL NETWORKS [J].

LIU, D ;

MICHEL, AN .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 1994, 41 (04) :295-307

[7] ANALYSIS AND SYNTHESIS OF A CLASS OF DISCRETE-TIME NEURAL NETWORKS WITH MULTILEVEL THRESHOLD NEURONS [J].

SI, J ;

MICHEL, AN .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (01) :105-116

[8]

SI J, 1991, P ISCAS 91, V3, P1461

← 1 →