GENETIC ALGORITHM FOR CNN TEMPLATE LEARNING

被引：104

作者：

KOZEK, T

ROSKA, T

CHUA, LO

机构：

[1] HUNGARIAN ACAD SCI,INST COMP & AUTOMAT,H-1361 BUDAPEST 5,HUNGARY

[2] TECH UNIV BUDAPEST,H-1521 BUDAPEST,HUNGARY

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS | 1993年 / 40卷 / 06期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/81.238343

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A new learning algorithm for space invariant cellular neural networks (CNN's) is described. Learning is formulated as an optimization problem. Exploration of any specified domain of stable CNN's is possible by the current approach. Templates are derived using a genetic optimization algorithm. Details of the algorithm are discussed and several application results are shown. Using this algorithm propagation-type and gray-scale-output CNN's can also be designed.

引用

页码：392 / 402

页数：11

共 15 条

[1] CELLULAR NEURAL NETWORKS - APPLICATIONS [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290

[2] CELLULAR NEURAL NETWORKS - THEORY [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272

[3] STABILITY OF A CLASS OF NONRECIPROCAL CELLULAR NEURAL NETWORKS [J].

CHUA, LO ;

ROSKA, T .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (12) :1520-1527

[4]

CHUA LO, 1991, INP RESS INT J CIRCU

[5]

CROUNSE KR, 1991, UCBERLM91106 U CAL B

[6]

Holland J., 1989, GENETIC ALGORITHMS S

[7] CNN CLONING TEMPLATE - SHADOW DETECTOR [J].

MATSUMOTO, T ;

CHUA, LO ;

SUZUKI, H .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (08) :1070-1073

[8] CNN CLONING TEMPLATE - CONNECTED COMPONENT DETECTOR [J].

MATSUMOTO, T ;

CHUA, LO ;

SUZUKI, H .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (05) :633-635

[9]

ROSKA T, 1990, P IEEE INT WORKSHOP, P12

[10]

ROSKA T, 1992, UNPUB DNS21992

← 1 2 →