Convergence dynamics of hybrid bidirectional associative memory neural networks with distributed delays
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 55-64 |
Journal / Publication | Physics Letters, Section A: General, Atomic and Solid State Physics |
Volume | 316 |
Issue number | 1-2 |
Publication status | Published - 15 Sep 2003 |
Link(s)
Abstract
In this Letter, the characteristics of the convergence dynamics of hybrid bidirectional associative memory neural networks with distributed transmission delays are studied. Without assuming the symmetry of synaptic connection weights and the monotonicity and differentiability of activation functions, the Lyapunov functionals are constructed and the generalized Halanay-type inequalities are employed to derive the delay-independent sufficient conditions under which the networks converge exponentially to the equilibria associated with temporally uniform external inputs. Some examples are given to illustrate the correctness of our results. © 2003 Elsevier B.V. All rights reserved.
Research Area(s)
- Bidirectional associative memory, Distributed delays, Global exponential stability, Neural networks
Citation Format(s)
Convergence dynamics of hybrid bidirectional associative memory neural networks with distributed delays. / Liao, Xiaofeng; Wong, Kwok-Wo; Yang, Shizhong.
In: Physics Letters, Section A: General, Atomic and Solid State Physics, Vol. 316, No. 1-2, 15.09.2003, p. 55-64.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review