[1]贺国旗[],韩泉叶[],陈绥阳[]. 外部输入与两单元CNN的完全稳定性[J].计算机技术与发展,2016,26(09):167-170.
　HE Guo-qi[],HAN Quan-ye[],CHEN Sui-yang[]. Complete Stability of Two-cell Cellular Neural Networks with External Inputs[J].,2016,26(09):167-170.
点击复制

 外部输入与两单元CNN的完全稳定性()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
26
期数:
2016年09期
页码:
167-170
栏目:
智能、算法、系统工程
出版日期:
2016-09-10

文章信息/Info

Title:
 Complete Stability of Two-cell Cellular Neural Networks with External Inputs
文章编号:
1673-629X（2016)09-00167-04
作者:
 贺国旗[1]; 韩泉叶[1] ; 陈绥阳[2]
 1.陕西广播电视大学；2.西安交通大学
Author(s):
 HE Guo-qi[1]; HAN Quan-ye[1] ; CHEN Sui-yang[2]
关键词:
 ; 细胞神经网络; 齐点 ; 极限环; 稳定性
Keywords:
 ; CNN; fixed point ; limit cycle; complete stability
分类号:
TP391
文献标志码:
A
摘要:
 细胞神经网络( CNN)在图像处理、模式识别等领域有非常广泛的应用，应用的基础取决于对网络动力学特性的认识，尤其是网络在什么条件下有极限环，什么条件下是稳定的。研究了一类在没有外部输入条件下已经被证明是不稳定的两单元细胞神经网络( CNN)在加上外部输入后的特性。该网络在不加外部输入时的特点是：全局只在0区存在唯一齐点，并且存在一个围绕0区的极限环。证明：加上外部输入后，外部输入在一定的区域取值，网络仍保持这样的特点，即网络仍不是完全稳定的，存在一个围绕0区的极限环。这表明，不加外部输入时的情况只是加外部输入的一种特例。此外，还给出了这个外部输入值的取值区域。这个两单元细胞神经网络的结果有助于进一步研究较大规模细胞神经网络的非线性动力学特性，也有助于进一步拓展其在函数逼近、模式识别及图像处理等方面的应用。
Abstract:
 Cellular neural networks have been widely used in image processing,pattern recognition and other fields. The base of the appli-cations is the realization of the dynamics,especially when there will be a limit cycle and how the network is stable. In this paper,a case of two-cell cellular neural networks with external inputs is studied which has been proved it is not completely stable without external inputs. The feature of the network without external inputs is that there is only one fixed point in region 0 and there is a limit cycle around region 0. It will prove that with external inputs and their values in given domain,the network still has the feature that it is not completely stable and there is a limit cycle around region 0. This indicates the CNN(2) without external inputs is only a special sub-case of that with exter-nal inputs. The domain of the external inputs values is also given. The result has expanded the understandings about the dynamics of the CNN(2) . He results on two-cell cellular neural networks will help to further study the nonlinear dynamics of large-scale cellular neural networks,and will also help to further expand its applications in function approximation,pattern recognition,image processing,and others.

相似文献/References:

[1]卢珊萍 于盛林.基于粒子群算法的细胞神经网络模板参数设计[J].计算机技术与发展,2009,(04):83.
　LU Shan-ping,YU Sheng-lin.A Template Design Method for Cellular Neural Network Based on Particle Swarm Optimizer Algorithm[J].,2009,(09):83.
[2]程莹 刘文波.基于自适应遗传算法的细胞神经网络模板设计[J].计算机技术与发展,2008,(05):54.
　CHENG Ying,LIU Wen-bo.Design on CNN Template Parameters Based on Adaptive Genetic Algorithm[J].,2008,(09):54.
[3]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(09):1.
[4]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(09):5.
[5]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(09):13.
[6]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(09):21.
[7]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(09):25.
[8]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(09):29.
[9]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(09):34.
[10]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
　SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(09):38.

更新日期/Last Update: 2016-10-26