Optimal solutions for cellular neural networks by paralleled hardware annealing

被引:8
作者
Bang, SH [1 ]
Sheu, BJ [1 ]
Wu, THY [1 ]
机构
[1] UNIV SO CALIF,INTEGRATED MEDIA SYST CTR,LOS ANGELES,CA 90089
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1996年 / 7卷 / 02期
关键词
D O I
10.1109/72.485679
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks are very promising in solving many scientific problems in image processing, pattern recognition, and optimization by the use of stored program with predetermined templates. Hardware annealing, which is a paralleled version of mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions of cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed annealing can be described by the eigenvalue problems in the time-varying dynamic system, In typical nonoptimization problems, it also provides enough stimulation to frozen neurons caused by ill-conditioned initial states.
引用
收藏
页码:440 / 454
页数:15
相关论文
共 29 条
[1]  
[Anonymous], INTRO NUMERICAL SOLU
[2]  
BANG S, 1993, P INT WRKSHP APPL NE
[3]  
Chen C.-T., 1998, LINEAR SYSTEM THEORY
[4]   CELLULAR NEURAL NETWORKS - APPLICATIONS [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290
[5]   CELLULAR NEURAL NETWORKS - THEORY [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272
[6]   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
[7]  
Cichocki A., 1993, Neural Networks for Optimization and Signal Processing
[8]   IMAGE HALF-TONING WITH CELLULAR NEURAL NETWORKS [J].
CROUNSE, KR ;
ROSKA, T ;
CHUA, LO .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1993, 40 (04) :267-283
[9]   A CNN CHIP FOR CONNECTED COMPONENT DETECTION [J].
CRUZ, JM .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1991, 38 (07) :812-817
[10]   AN ANALOG IMPLEMENTATION OF DISCRETE-TIME CELLULAR NEURAL NETWORKS [J].
HARRER, H ;
NOSSEK, JA ;
STELZL, R .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (03) :466-476