[1]王友国,姜梦琦,翟其清. 多阈值神经网络系统中的随机共振研究[J].计算机技术与发展,2015,25(12):32-36.
　ANG You-guo,JIANG Meng-qi,ZHAI Qi-qing. Research on Stochastic Resonance in Multi-threshold Neural Network System[J].,2015,25(12):32-36.
点击复制

 多阈值神经网络系统中的随机共振研究()
分享到：

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

卷:
25
期数:
2015年12期
页码:
32-36
栏目:
智能、算法、系统工程
出版日期:
2015-12-10

文章信息/Info

Title:
 Research on Stochastic Resonance in Multi-threshold Neural Network System
文章编号:
1673-629X（2015)12-0032-05
作者:
 王友国; 姜梦琦; 翟其清
 南京邮电大学 通信与信息工程学院
Author(s):
 ANG You-guo; JIANG Meng-qi; ZHAI Qi-qing
关键词:
 ; 和平均网络; 中心极限定理; 互信息; 阈上随机共振
Keywords:
 ; sum-and-average network; central limit theorem; mutual information; supra-threshold stochastic resonance
分类号:
TP31
文献标志码:
A
摘要:
 文中研究了求和平均网络中的互信息随噪声强度的变化关系. 将神经网络模型中典型的求和网络改进为求和平均网络,采用中心极限定理,将输出信号近似为连续的高斯分布,得到输入、输出均为连续信号时的系统互信息,基于此互信息研究了在加性噪声和乘性噪声共同作用下多阈值神经网络系统中的阈上随机共振现象. 研究结果表明,对每一个固定的系统阈值,改变加性噪声强度比改变乘性噪声强度更能诱导阈上随机共振. 另外,系统阈值的增加使信号主要成分在阈下,更能诱导阈上随机共振,但会降低阈上随机共振的功效. 乘性或加性噪声强度以及系统阈值水平是阈上随机共振现象产生的重要条件,噪声强度以及系统阈值的适当选取会使得阈上随机共振现象更加明显.
Abstract:
 In this paper,the relationship between the mutual information and the noise intensity of the mutual information in the sum-and-average network is studied. The typical sum-network in neural networks is improved to sum-and-average network. By using the central limit theorem,output signal is approximated as continuous Gaussian distribution,and mutual information can be obtained when the input and output signals are all continuous. Based on this mutual information,a study is made on the Supra-threshold Stochastic Resonance ( SSR) phenomenon under both additive and multiplicative noise in a multi-threshold neural networks system. The numerical calculation and the computer simulation found that for a fixed system threshold,by changing the additive noise intensity SSR occurs more easily than by changing the multiplicative noise intensity. In addition,the increase of the system threshold can increase the signal components that are under the threshold,and thus SSR takes place more easily,but cut down the efficiency of SSR at the same time. The multiplicative or ad-ditive noise intensity,and the system threshold level are important factors to stimulate SSR. A reasonable noise intensity and threshold val-ue would lead to a more significant SSR.

相似文献/References:

[1]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(12):1.
[2]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(12):5.
[3]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(12):13.
[4]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(12):21.
[5]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(12):25.
[6]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(12):29.
[7]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(12):34.
[8]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(12):38.
[9]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
　YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(12):43.
[10]余松平[][],蔡志平[],吴建进[],等. GSM-R信令监测选择录音系统设计与实现[J].计算机技术与发展,2014,24(07):47.
　YU Song-ping[][],CAI Zhi-ping[] WU Jian-jin[],GU Feng-zhi[]. Design and Implementation of an Optional Voice Recording System Based on GSM-R Signaling Monitoring[J].,2014,24(12):47.

更新日期/Last Update: 2016-01-28