Dynamical behaviors of delayed neural network systems with discontinuous activation functions. (English) Zbl 1094.68625

Summary: In this letter, without assuming the boundedness of the activation functions, we discuss the dynamics of a class of delayed neural networks with discontinuous activation functions. A relaxed set of sufficient conditions is derived, guaranteeing the existence, uniqueness, and global stability of the equilibrium point. Convergence behaviors for both state and output are discussed. The constraints imposed on the feedback matrix are independent of the delay parameter and can be validated by the linear matrix inequality technique. We also prove that the solution of delayed neural networks with discontinuous activation functions can be regarded as a limit of the solutions of delayed neural networks with high-slope continuous activation functions.


68T05 Learning and adaptive systems in artificial intelligence
Full Text: DOI


[1] DOI: 10.1016/S0893-6080(01)00059-4 · Zbl 02022167
[2] DOI: 10.1109/81.222796 · Zbl 0792.68115
[3] DOI: 10.1109/TSMC.1983.6313075 · Zbl 0553.92009
[4] DOI: 10.1137/0305040 · Zbl 0238.34010
[5] DOI: 10.1109/TCSI.2003.818614 · Zbl 1368.34024
[6] DOI: 10.1016/0022-0396(81)90031-0 · Zbl 0472.34043
[7] DOI: 10.1109/72.129419
[8] DOI: 10.1073/pnas.81.10.3088 · Zbl 1371.92015
[9] DOI: 10.1126/science.3755256
[10] DOI: 10.1016/S0893-6080(00)00042-3
[11] DOI: 10.1109/31.1783
[12] DOI: 10.1090/S0002-9939-02-06480-8 · Zbl 1013.34066
[13] DOI: 10.1016/j.neunet.2004.09.004 · Zbl 1078.68127
[14] Lu W. L., Int. J. Neural Networks 13 pp 193– (2003)
[15] DOI: 10.1109/TCS.1987.1086038 · Zbl 0632.34005
[16] DOI: 10.1006/jmaa.1996.0099 · Zbl 0854.34012
[17] DOI: 10.1109/TAC.1977.1101446 · Zbl 0382.93036
[18] DOI: 10.1109/TCSI.2003.817760 · Zbl 1368.34089
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.