TY - GEN
T1 - On stability of multiple equilibria for delayed neural networks with discontinuous activation functions
AU - Nie, Xiaobing
AU - Zheng, Wei Xing
PY - 2015
Y1 - 2015
N2 - This paper considers the stability problem of multiple equilibria for delayed neural networks with discontinuous activation functions. By virtue of the fixed point theorem, it is found that under some sufficient conditions, n neurons delayed neural networks with discontinuous non-monotonic activation functions can have at least 4â„¢ equilibrium points and 3â„¢ of them are locally stable. Furthermore, it is shown that the storage capacity of the neural networks can be considerably expanded by use of discontinuous activation functions, which is important in several neural network applications. Finally, the effectiveness of the theoretical findings is verified by a numerical example.
AB - This paper considers the stability problem of multiple equilibria for delayed neural networks with discontinuous activation functions. By virtue of the fixed point theorem, it is found that under some sufficient conditions, n neurons delayed neural networks with discontinuous non-monotonic activation functions can have at least 4â„¢ equilibrium points and 3â„¢ of them are locally stable. Furthermore, it is shown that the storage capacity of the neural networks can be considerably expanded by use of discontinuous activation functions, which is important in several neural network applications. Finally, the effectiveness of the theoretical findings is verified by a numerical example.
KW - multistability
KW - neural networks (computer science)
KW - time delay systems
UR - http://handle.uws.edu.au:8081/1959.7/uws:32781
UR - http://ccc-sice2015.hdu.edu.cn/
U2 - 10.1109/ChiCC.2015.7260185
DO - 10.1109/ChiCC.2015.7260185
M3 - Conference Paper
SN - 9781467374439
SP - 3542
EP - 3547
BT - Proceedings of 34th Chinese Control Conference (CCC2015), July 28-30, 2015, Hangzhou, China
PB - IEEE
T2 - Chinese Control Conference
Y2 - 28 July 2015
ER -