摘要
讨论时标上的一类带有McCulloch-Pitts型信号函数的二元神经网络模型的渐进行为,根据信号函数的特点,将模型转化为时标上的4个方程组来考虑,应用时标的微分系统的基本理论,通过对建立的一维映射的迭代规律进行分析,得到该神经网络模型的收敛性.
A network of two neurons with McCulloch-Pitts signal function is considered. According to the signal function, analysis of the dynamics of the network is equivalent to discussing four corresponding systems of linear non-homogeneous ordinary differential equations on time scales. The dynamics of the network can be understood in terms of the iterations of a one dimensional mapping, and we obtain the convergence of solutions.
出处
《河南工程学院学报(自然科学版)》
2008年第2期72-74,共3页
Journal of Henan University of Engineering:Natural Science Edition
关键词
时标
神经网络
渐进性
时滞
time scale
neurons network
asymptotic behavior
time delay