非对称反馈神经网络中亚稳态的位置与稳定性  

The position and stability of metastable states in asymmetric feedback neural networks

作　　者：方一博[1] 金涛[1] 屈世显[1] 

机构地区：[1]陕西师范大学物理学与信息技术学院,陕西西安710062

出　　处：《陕西师范大学学报（自然科学版）》2013年第5期46-49,共4页Journal of Shaanxi Normal University：Natural Science Edition

基　　金：国家自然科学基金资助项目(10875076);陕西省自然科学基金资助项目(SJ08A23)

摘　　要：研究了由广义感知机学习规则设计的单层反馈神经网络中亚稳态的相空间位置,通过计算亚稳态与基态之间的汉明距离(Hamming distance),发现该系统的亚稳态集中出现在与各基态近似等距离的位置.进一步计算了亚稳态与基态的能量比,发现调节控制参数能有效减弱亚稳态对系统的影响.The positions of metastable states of single-layer feedback neural network designed by the generalized perceptron rule are investigated in the phase space. The Hamming distance between metastable states and ground states is calculated, which shows that the metastable states concentrate in the positions where approximately equidistant to all the ground states. In addition, the energy ratio of metastable states and ground states are calculated, which can be found that the influence of metastable states can be weakened by adjusting the parameter k.

关 键 词：神经网络 亚稳态 相空间位置 稳定性 

分 类 号：O415.6[理学—理论物理]