耦合神经网络中脉冲信号传输的噪声增强研究  

Study of Noise-Enhanced Pulse Signal Transmission in Coupling Neural Networks

作　　者：方鸿雁[1] 潘园园[1] 孙华通 张立[1] 段法兵[1] 

机构地区：[1]青岛大学复杂性科学研究所,山东青岛266071

出　　处：《复杂系统与复杂性科学》2017年第2期59-64,共6页Complex Systems and Complexity Science

基　　金：国家自然科学基金(61573202);山东省科技发展计划(ZR2010FM006)

摘　　要：对积分发放神经元耦合网络中脉冲信号传输的噪声增强现象进行了研究。通过权矩阵控制神经元间耦合强度和网络结构,网络中脉冲刺激信号激励靶神经元,而网络内各神经元都受到内部噪声的驱动。研究表明,随着噪声强度的增加,神经网络输出发放率与离散脉冲信号发放率的互相关系数不断增加并达到极值,证实了脉冲信号传输中耦合神经网络中存在噪声增强现象。还进一步分析了门限电势、网络结构以及噪声类型对输入输出发放率之间互相关系数的影响。这些研究结果为进一步将随机共振理论应用到神经系统中脉冲信号传递问题提供了实际依据。This paper studies the noise-enhanced pulse signal transmission in coupling neural networks composed of integrate-and-fire neurons.The coupling strengthsamong neurons and the structure of the network are described by the weight matrices.The input pulse stimulus is delivered to target neurons of the network,while all neurons in the network are driven by internal noise components.It is shown that,with the increase of noise intensity,the correlation coefficient of the firing rate of the neural network output and that of the pulse stimulus can be enhanced to an extreme point,which confirms the noise-enhanced pulse signal transmission phenomenon in coupling networks.We further analyze effects of the threshold voltage,the structure of network and the noise type on the correlation coefficient of the output-input firing rates.These results provide a practical basis for the further study of stochastic resonance to the pulse signal propagation in nervous systems.

关 键 词：耦合神经网络 噪声增强 脉冲信号 互相关系数 积分发放神经元 

分 类 号：TN911.7[电子电信—通信与信息系统] N945.12[电子电信—信息与通信工程]