Title :
Global Attractivity of Discrete-Time Recurrent Neural Networks With Lnsaturating Piecewise Linear Activation Functions
Author :
Qu, Hong ; Yi, Zhang
Author_Institution :
Comput. Intelligence Lab., UESTC, Chengdu
Abstract :
Multistable networks have attracted much interests in recent years, since the monostable networks are computationally restricted. This paper studies the global attractivity of a class of discrete-time recurrent neural networks with unsaturating piecewise linear activation function. Some conditions are derived by mathematical analysis to guarantee the boundedness and global attractivity of the networks. Simulation examples are used to illustrate the theory developed in this paper
Keywords :
discrete time systems; mathematical analysis; piecewise linear techniques; recurrent neural nets; stability; transfer functions; discrete-time recurrent neural networks; global attractivity; mathematical analysis; multistable networks; unsaturating piecewise linear activation functions; Computational intelligence; Computer networks; Electronic mail; Equations; Laboratories; Mathematical analysis; Neural networks; Neurons; Piecewise linear techniques; Recurrent neural networks;
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
DOI :
10.1109/ICNNB.2005.1614584
