|
|
||||||||
Letter |
02108041{at}fudan.edu, wenlian{at}mis.mpg.de
tchen{at}fudan.edu.cn Laboratory of Nonlinear Mathematics Science, Institute of Mathematics, Fudan University, Shanghai, 200433, People's Republic of China
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.
This article has been cited by other articles:
![]() |
Q. Liu and J. Wang A One-Layer Recurrent Neural Network with a Discontinuous Activation Function for Linear Programming Neural Comput., May 1, 2008; 20(5): 1366 - 1383. [Abstract] [Full Text] [PDF] |
||||
![]() |
W. Lu and T. Chen Almost Periodic Dynamics of a Class of Delayed Neural Networks with Discontinuous Activations Neural Comput., April 1, 2007; 20(4): 1065 - 1090. [Abstract] [Full Text] [PDF] |
||||
![]() |
X. Lou and B. Cui Boundedness and stability for integrodifferential equations modeling neural field with time delay. Neural Comput., February 1, 2007; 19(2): 570 - 581. [Abstract] [Full Text] [PDF] |
||||
| HOME | HELP | FEEDBACK | SUBSCRIPTIONS | ARCHIVE | SEARCH | TABLE OF CONTENTS |
| J COGNITIVE NEUROSCIENCE | NEURAL COMPUTATION | MIT PRESS JOURNALS |