《计算机应用研究》|Application Research of Computers

具有漏泄时滞的随机神经网络的均方指数稳定性

Mean square exponential stability of stochastic neural networks with time delays in leakage terms

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王芬
机构 广东金融学院 金融数学与统计学院,广州 510521
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)10-2904-04
DOI 10.3969/j.issn.1001-3695.2018.10.005
摘要 在实现复杂的人工神经网络模型的过程中,随机噪声是不可避免的。建立具有随机噪声干扰的神经网络模型不但是设计上的需要,而且能够更加真实地反映生物神经网络的特点。利用构造合适的Lyapunov泛函、应用It微分公式及Jensen不等式性质等,研究了一类具有漏泄时滞的随机神经网络的动力学行为,得到了确保该系统均方指数稳定的充分判别条件。最后,通过两个数值计算的例子说明了所得结论的有效性。
关键词 随机;神经网络;均方指数稳定;时滞
基金项目 广东省自然科学基金资助项目(2015A030310426)
广东省普通高校青年创新人才资助项目(自然科学类)(2014KQNCX187)
广东省高等学校优秀青年教师培养计划资助项目(YQ2015118)
广东省普通高校特色创新类项目(教育科研项目)(2016GXJK117)
广东省教育厅创新强校工程资助项目(0000-E205010015005017,20170504185)
本文URL http://www.arocmag.com/article/01-2018-10-005.html
英文标题 Mean square exponential stability of stochastic neural networks with time delays in leakage terms
作者英文名 Wang Fen
机构英文名 SchoolofFinancialMathematics&Statistics,GuangdongUniversityofFinance,Guangzhou510521,China
英文摘要 Random noise is unavoidable in the process of implementing a complex artificial neural network model. Establi-shing a neural network model with random noise interference is not only the need of design, but also can reflect the characteristics of biological neural network more truly. By employing appropriate Lyapunov functional, It differential formula and Jensen inequality, this paper studied the dynamical behavior of a class of stochastic neural networks with time delays in leakage terms. It obtained several sufficient conditions for ensuring the system to be mean square exponential stability. Finally, two illustrative examples show the effectiveness of the results.
英文关键词 stochastic; neural networks; mean square exponential stability; delay times
参考文献 查看稿件参考文献
  [1] 王山海, 景新幸, 杨海燕. 基于深度学习神经网络的孤立词语音识别的研究[J] . 计算机应用研究, 2015, 32(8):2289-2291, 2298.
[2] 杨海燕, 蒋新华, 聂作先. 基于并行卷积神经网络的人脸关键点定位方法研究[J] . 计算机应用研究, 2015, 32(8):2517-2519.
[3] Li Hongfei, Jiang Haijun, Hu Cheng. Existence and global exponential stability of periodic solution of memristor-based BAM neural networks with time-varying delays[J] . Neural Networks, 2016, 75(3):97-109.
[4] Chen Liping, Wu Ranchao, Cao Jinde, et al. Stability and synchronization of memristor-based fractional-order delayed neural networks[J] . Neural Networks, 2015, 71(11):37-44.
[5] Wang Fen, Sun Dong, Wu Huaiyu. Global exponential stability and periodic solutions of high-order bidirectional associative memory (BAM) neural networks with time delays and impulses[J] . Neurocomputing, 2015, 155(5):261-276.
[6] Zhu Song, Shen Yi, Chen Guici. Exponential passivity of neural networks with time-varying delay and uncertainty[J] . Physics Letters A, 2010, 375(2):136-142.
[7] Yang Xujun, Song Qiankun, Liu Yurong, et al. Finite-time stability analysis of fractional-order neural networks with delay[J] . Neurocomputing, 2015, 152(3):19-26.
[8] 马亚明, 温博慧. 资产价格与宏观经济金融系统的稳定性——基于货币量值模型的理论与仿真分析[J] . 金融经济学研究, 2013, 28(5):49-63.
[9] Rao Ruofeng, Zhong Shouming, Wang Xiongrui. Stochastic stability criteria with LMI conditions for Markovian jumping impulsive BAM neural networks with mode-dependent time-varying delays and nonlinear reaction-diffusion[J] . Communications in Nonlinear Science & Numerical Simulation, 2014, 19(1):258-273.
[10] Liu Linna, Zhu Quanxin. Almost sure exponential stability of numerical solutions to stochastic delay Hopfield neural networks[J] . Applied Mathematics and Computation, 2015, 266(9):698-712.
[11] Li Jun, Hu Manfeng, Guo Liuxiao. Exponential stability of stochastic memristor-based recurrent neural networks with time-varying delays[J] . Neurocomputing, 2014, 138(8):92-98.
[12] Song Qiankun, Liang Jinling, Wang Zidong. Passivity analysis of discrete-time stochastic networks with time-varying delays[J] . Neurocomputing, 2009, 72(7~9):1782-1788.
[13] Huang Chuangxia, He Yigang, Huang Lihong, et al. pth moment stability analysis of stochastic recurrent neural networks with time-varying delays[J] . Information Sciences, 2008, 178(9):2194-2203.
[14] 罗兰, 钟守铭. 具有泄露时滞和反应扩散的随机模糊细胞神经网络的吸引与最终有界[J] . 西南民族大学学报:自然科学版, 2012, 38(5):724-731.
[15] 王军涛, 郑群珍, 苏展, 等. 具有漏泄时滞和时变区间时滞的递归神经网络新的稳定性准则[J] . 河南师范大学学报:自然科学版, 2016, 44(3):166-177.
[16] Liu Xinzhi, Teo K L, Xu Bingji. Exponential stability of impulsive high-order Hopfield-type neural networks with time-varying delays[J] . IEEE Trans on Neural Networks, 2005, 16(6):1329-1339.
[17] Park M J, Kwon O M, Park J H, et al. Synchronization criteria for coupled stochastic neural networks with time-varying delays and leakage delay[J] . Journal of the Franklin Institute, 2012, 349(5):1699-1720.
[18] Qiu Jianlong. Dynamics of high-order Hopfield neural networks with time delays[J] . Neurocomputing, 2010, 73(4-6):820-826.
[19] 梅生伟, 申铁龙, 刘康志. 现代鲁棒控制理论与应用[M] . 北京:清华大学出版社, 2003:93.
收稿日期 2017/5/23
修回日期 2017/7/17
页码 2904-2907
中图分类号 TP183
文献标志码 A