混沌神经网络的动态阈值控制

张旭东; 朱萍; 谢小平; 何国光

doi:10.7498/aps.62.210506

摘要

提出了混沌神经网络的动态阈值控制方法, 将大脑脑电波的主要成分, 正弦信号作为控制变量实现对混沌神经网络内部状态的阈值动态改变, 从而达到了控制混沌神经网络混沌的目的. 利用该方法可以将混沌神经网络的输出稳定在一个与网络初始模式相关的存储模式和其反相模式上, 从而使混沌神经网络在模式识别、信息搜索等信息处理功能得以实现. 该控制方法不需要事先指定阈值, 是一种自适应方法, 符合实际人脑的思维运动.

关键词:

Abstract

A dynamic threshold value control method is proposed to get control over a chaotic neural network (CNN). The sinusoidal signal, which constitutes the key component of the brain wave, is taken as the control signal to change the threshold value of the internal states of the CNN. The chaos control of the CNN is therefore reached with its outputs of the controlled CNN reciprocating between a stored pattern and its reverse pattern related with the initial pattern. And then the CNN can be applied in information processing, such as pattern recognitionetc. The chaos control method works in a self-adaption way since it does not need to set the threshold value beforehand, which is in accordance with brains’ thinking activities.

Keywords:

作者及机构信息

1.
浙江大学物理学系, 杭州 310027

基金项目: 国家自然科学基金 (批准号: 61175060)和浙江大学物理学人才培养基地–科研训练及科研能力提高项目(批准号: J1210046)资助的课题.

Authors and contacts

1.
Department of Physics, Zhejiang University, Hangzhou 310027, China

Funds: Project supported by the National Natural Science Foundation of China (Grant No. 61175060), and the Research Training and Research Ability Enhancement in Physics Fostering Talents of Zhejiang University (Grant No. J1210046).

参考文献

[1]	Aihara K, Takabe T, Toyoda M 1990 Phys. Lett. A 144 333
[2]	Tokuda I, Nagashima T, Aihara K 1997 Neural Networks. 10 1673
[3]	Wang B Y, Nie J N, He Z Y 1999 IEEE Trans. on Neural Networks. 10 1257
[4]	Ott E, Grebogi C, Yorke J A 1990 Phys. Rev. Lett. 64 1196
[5]	Pecora L M, Carroll T L 1990 Phys. Rev. Lett. 64 821
[6]	Huberman B A, Lumer E 1990 IEEE Trans. on Circuits Syst. 37 547
[7]	Hunt E R 1991 Phys. Rev. Lett. 67 1953
[8]	Pyragas K, Tamasericius A 1992 Phys. Lett. A 170 421
[9]	Luo X S, Fang J Q, Kong L J 2000 Acta Phys. Sin. 49 1423 (in Chinese) [罗晓曙, 方锦清, 孔令江 2000 49 1423]
[10]	Chen S H, Liu J, Xie J 2002 Chin. Phys. 11 233
[11]	L J H, Zhou T S, Zhang S C 2002 Chin. Phys. 11 12
[12]	Li L X, Peng H P, Lu H B 2001 Chin. Phys. 10 796
[13]	Li X L, Fu D X, Ma Y W 2006 Chin. Phys. Lett. 23 1519
[14]	Sang H B, He K F 2004 Chin. Phys. Lett. 21 254
[15]	Fahy S, Hamann D R 1992 Phys. Rev. Lett. 69 761
[16]	Luo X S, Wang B H, Chen G R 2002 Acta Phys. Sin. 51 988 (in Chinese) [罗晓曙, 汪秉宏, 陈关荣 2002 51 988]
[17]	Sang H B, He K F 2004 Chin. Phys. Lett. 21 254
[18]	Huang L Y, Luo X S 2006 Chin. Phys. Lett. 23 297
[19]	He G G, Cao Z T 2001 Acta Phys. Sin. 50 2103 (in Chinese) [何国光, 曹志彤 2001 50 2103]
[20]	He G, Chen L, Aihara K 2008 Neurocomputing 71 2794
[21]	He G, Shrimali M D, Aihara K 2007 Physics Letters A 371 228
[22]	He G, Shrimali M D, Aihara K 2008 Neural networks 21 114
[23]	He G G, Zhu P, Chen H P 2010 Acta Phys. Sin. 59 140 (in Chinese) [何国光, 朱萍, 陈宏平 2010 59 140]
[24]	He G, Cao Z, Chen H, Zhu P 2003 International Journal of Modern Physics B 17 4209
[25]	Zhang X, Shen K 2001 Phys. Rev. E 63 046212
[26]	Watanabe M, Aihara K, Kondo S 1996 Electron. Commun. Japan Part III 79 87
[27]	Osana Y, Hagiwara M 1999 Internat. J. Neural Syst. 9 285
[28]	Wang Z, Fan H, Aihara K 2007 Internat. J. Bifur. Chaos 17 3085
[29]	Li Y, Zhu P, Xie X, He G, Aihara K 2012 Phys. Lett. A 376 412
[30]	Sih G C, Tang K K 2012 Theoretical and Applied Fracture Mechanics 61 21
[31]	Freeman W J, Viana Di Prisco G 1986 Brain Theory (Berlin: Springer-Verlag) p97
[32]	Freeman W J 1987 Biological Cybernetics 56 139

施引文献

[1]	Aihara K, Takabe T, Toyoda M 1990 Phys. Lett. A 144 333
[2]	Tokuda I, Nagashima T, Aihara K 1997 Neural Networks. 10 1673
[3]	Wang B Y, Nie J N, He Z Y 1999 IEEE Trans. on Neural Networks. 10 1257
[4]	Ott E, Grebogi C, Yorke J A 1990 Phys. Rev. Lett. 64 1196
[5]	Pecora L M, Carroll T L 1990 Phys. Rev. Lett. 64 821
[6]	Huberman B A, Lumer E 1990 IEEE Trans. on Circuits Syst. 37 547
[7]	Hunt E R 1991 Phys. Rev. Lett. 67 1953
[8]	Pyragas K, Tamasericius A 1992 Phys. Lett. A 170 421
[9]	Luo X S, Fang J Q, Kong L J 2000 Acta Phys. Sin. 49 1423 (in Chinese) [罗晓曙, 方锦清, 孔令江 2000 49 1423]
[10]	Chen S H, Liu J, Xie J 2002 Chin. Phys. 11 233
[11]	L J H, Zhou T S, Zhang S C 2002 Chin. Phys. 11 12
[12]	Li L X, Peng H P, Lu H B 2001 Chin. Phys. 10 796
[13]	Li X L, Fu D X, Ma Y W 2006 Chin. Phys. Lett. 23 1519
[14]	Sang H B, He K F 2004 Chin. Phys. Lett. 21 254
[15]	Fahy S, Hamann D R 1992 Phys. Rev. Lett. 69 761
[16]	Luo X S, Wang B H, Chen G R 2002 Acta Phys. Sin. 51 988 (in Chinese) [罗晓曙, 汪秉宏, 陈关荣 2002 51 988]
[17]	Sang H B, He K F 2004 Chin. Phys. Lett. 21 254
[18]	Huang L Y, Luo X S 2006 Chin. Phys. Lett. 23 297
[19]	He G G, Cao Z T 2001 Acta Phys. Sin. 50 2103 (in Chinese) [何国光, 曹志彤 2001 50 2103]
[20]	He G, Chen L, Aihara K 2008 Neurocomputing 71 2794
[21]	He G, Shrimali M D, Aihara K 2007 Physics Letters A 371 228
[22]	He G, Shrimali M D, Aihara K 2008 Neural networks 21 114
[23]	He G G, Zhu P, Chen H P 2010 Acta Phys. Sin. 59 140 (in Chinese) [何国光, 朱萍, 陈宏平 2010 59 140]
[24]	He G, Cao Z, Chen H, Zhu P 2003 International Journal of Modern Physics B 17 4209
[25]	Zhang X, Shen K 2001 Phys. Rev. E 63 046212
[26]	Watanabe M, Aihara K, Kondo S 1996 Electron. Commun. Japan Part III 79 87
[27]	Osana Y, Hagiwara M 1999 Internat. J. Neural Syst. 9 285
[28]	Wang Z, Fan H, Aihara K 2007 Internat. J. Bifur. Chaos 17 3085
[29]	Li Y, Zhu P, Xie X, He G, Aihara K 2012 Phys. Lett. A 376 412
[30]	Sih G C, Tang K K 2012 Theoretical and Applied Fracture Mechanics 61 21
[31]	Freeman W J, Viana Di Prisco G 1986 Brain Theory (Berlin: Springer-Verlag) p97
[32]	Freeman W J 1987 Biological Cybernetics 56 139

[1]	胡志强, 李文静, 乔俊飞. 变频正弦混沌神经网络及其应用. , 2017, 66(9): 090502. doi: 10.7498/aps.66.090502
[2]	于舒娟, 宦如松, 张昀, 冯迪. 基于混沌神经网络的盲检测改进新算法. , 2014, 63(6): 060701. doi: 10.7498/aps.63.060701
[3]	曾喆昭. 不确定混沌系统的径向基函数神经网络反馈补偿控制. , 2013, 62(3): 030504. doi: 10.7498/aps.62.030504
[4]	缪志强, 王耀南. 基于径向小波神经网络的混沌系统鲁棒自适应反演控制. , 2012, 61(3): 030503. doi: 10.7498/aps.61.030503
[5]	朱少平, 钱富才, 刘丁. 不确定动态混沌系统的最优控制. , 2010, 59(4): 2250-2255. doi: 10.7498/aps.59.2250
[6]	高继华, 谢玲玲, 彭建华. 利用速度反馈方法控制时空混沌. , 2009, 58(8): 5218-5223. doi: 10.7498/aps.58.5218
[7]	楼旭阳, 崔宝同. 混沌时滞神经网络系统的反同步. , 2008, 57(4): 2060-2067. doi: 10.7498/aps.57.2060
[8]	李爽, 徐伟, 李瑞红. 利用随机相位实现Duffing系统的混沌控制. , 2006, 55(3): 1049-1054. doi: 10.7498/aps.55.1049
[9]	司马文霞, 刘凡, 孙才新, 廖瑞金, 杨庆. 基于改进的径向基函数神经网络的铁磁谐振系统混沌控制. , 2006, 55(11): 5714-5720. doi: 10.7498/aps.55.5714
[10]	王占山, 张化光, 王智良. 一类混沌神经网络的全局同步. , 2006, 55(6): 2687-2693. doi: 10.7498/aps.55.2687
[11]	刘光杰, 单梁, 戴跃伟, 孙金生, 王执铨. 基于混沌神经网络的单向Hash函数. , 2006, 55(11): 5688-5693. doi: 10.7498/aps.55.5688
[12]	何国光, 朱萍, 陈宏平, 曹志彤. 混沌神经网络的延时反馈控制研究. , 2006, 55(3): 1040-1048. doi: 10.7498/aps.55.1040
[13]	刘涵, 刘丁, 任海鹏. 基于最小二乘支持向量机的混沌控制. , 2005, 54(9): 4019-4025. doi: 10.7498/aps.54.4019
[14]	龚礼华. 基于自适应脉冲微扰实现混沌控制的研究. , 2005, 54(8): 3502-3507. doi: 10.7498/aps.54.3502
[15]	于洪洁. 延迟-非线性反馈控制混沌. , 2005, 54(11): 5053-5057. doi: 10.7498/aps.54.5053
[16]	于灵慧, 房建成. 混沌神经网络逆控制的同步及其在保密通信系统中的应用. , 2005, 54(9): 4012-4018. doi: 10.7498/aps.54.4012
[17]	郭会军, 刘君华. 基于径向基函数神经网络的Lorenz混沌系统滑模控制. , 2004, 53(12): 4080-4086. doi: 10.7498/aps.53.4080
[18]	刘丁, 任海鹏, 孔志强. 基于径向基函数神经网络的未知模型混沌系统控制. , 2003, 52(3): 531-535. doi: 10.7498/aps.52.531
[19]	谭文, 王耀南, 刘祖润, 周少武. 非线性系统混沌运动的神经网络控制. , 2002, 51(11): 2463-2466. doi: 10.7498/aps.51.2463
[20]	何国光, 曹志彤. 混沌神经网络的控制. , 2001, 50(11): 2103-2107. doi: 10.7498/aps.50.2103

计量

文章访问数: 7141
PDF下载量: 582
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板