混沌神经网络的动态阈值控制  

A dynamic threshold value control method for chaotic neural networks

作　　者：张旭东[1] 朱萍[1] 谢小平[1] 何国光[1] 

机构地区：[1]浙江大学物理学系,杭州310027

出　　处：《物理学报》2013年第21期71-77,共7页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:61175060);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~~

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.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 pattem. 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.

关 键 词：混沌控制 混沌神经网络 动态阈值控制 信息处理 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]