A new stability criterion for bidirectional associative memory neural networks of neutral-type
Introduction
Since cellular neural networks have been introduced by Chua and Yang [1], extensive research on neural networks has been done by many scientists over the past years [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13]. Also, it is well known that a series of neural networks related to bidirectional associative memory (BAM) models have been proposed by Kosko [14], [15]. These models generalized the single-layer autoassociative Hebbian correlator to a two-layer pattern-matched heteroassociative circuit. This class of networks has been successfully applied to pattern recognition and artificial intelligence. Therefore, the BAM neural networks have been one of the most interesting research topics and have attracted the attention of many researchers [16], [17], [18], [19], [20]. Furthermore, since time delay will inevitably occur in the communication and response of neurons owing to the unavoidable finite switching speed of amplifiers in the electronic implementation of analog neural networks, so it is more in accordance with this fact to study the BAM neural networks with time delays. With regard to recent works, see [21], [22] and the references cited therein. On the other hand, due to the complicated dynamic properties of the neural cells in the real world, the existing neural network models in many cases cannot characterize the properties of a neural reaction process precisely. It is natural and important that systems will contain some information about the derivative of the past state to further describe and model the dynamics for such complex neural reactions [23]. However, the stability analysis of neural networks of neutral-type has been investigated by only a few researchers [23], [24], [25].
Motivated by the above statement, this paper considers asymptotic stability for BAM neural networks of neutral type for the first time. Based on the Lyapunov theory, a new stability criterion is given in terms of LMI. The advantage of the proposed approach is that resulting stability criterion can be performed efficiently via existing numerical convex optimization algorithms such as the interior-point algorithms for solving the linear matrix inequality inequalities [27].
Throughout the paper, a real symmetric matrix P > 0 (⩾0) denotes the matrix P being a positive definite (positive semidefinite) matrix. I denotes the identity matrix of appropriate dimension.
Section snippets
Problem statement
Consider the following BAM neural networks model:in which are the neuron state vectors, , , are the connection weights at the time t, denote the external inputs, are positive constants which correspond to the finite speed of axonal signal transmission, and . The activate
Main result
In this section, the asymptotical stability of equilibrium point of network (3) is considered. A new delay-dependent stability criterion, which can be solved effectively using convex optimization algorithms, is obtained by the Lyapunov analysis. Theorem 1 For given , and , the equilibrium point of Eq. (1) is asymptotically stable if there exist positive definite matrices , and any matrices , satisfying the following
Concluding remarks
In this paper, we have investigated the asymptotical stability of BAM neural network of neutral type for the first time. The Lyapunov method is used to get stability analysis. As a result, a novel delay-dependent criterion for the stability of the BAM network has been presented. The criterion is expressed by an LMI. The approach used in this paper can be generalized to the BAM network with time-varying delays or uncertainties. Finally, to show the effectiveness of the proposed criterion, a
Acknowledgement
This research was supported by the Yeungnam University research grants in 2007.
References (28)
- et al.
Novel delay-dependent robust stability criterion of delayed cellular neural networks
Chaos, Solitons & Fractals
(2007) A new stability analysis of delayed cellular neural networks
Applied Mathematics and Computation
(2006)Global exponential stability of cellular neural networks with variable delays
Applied Mathematics and Computations
(2006)- et al.
New exponential stability results for delayed neural networks with time varying delays
Physica D
(2004) A delay-dependent asymptotic stability criterion of cellular neural networks with time-varying discrete and distributed delays
Chaos, Solitons & Fractals
(2007)On global stability criterion for neural networks with discrete and distributed delays
Chaos Solitons & Fractals
(2006)- et al.
Global asymptotic stability for cellular neural networks with discrete and distributed time-varying delays
Chaos Solitons & Fractals
(2007) An analysis of global robust stability of uncertain cellular neural networks with discrete and distributed delays
Chaos, Solitons & Fractals
(2007)- et al.
A new approach to exponential stability analysis of neural networks with time-varying delays
Neural Networks
(2006) Global stability of bidirectional associative memory neural networks with distributed delays
Physics Letters A
(2002)
Global asymptotic stability of delayed bidirectional associative memory neural networks
Applied Mathematics and Computation
Existence and stability of almost periodic solution for BAM neural networks with delays
Applied Mathematics and Computation
Robust stability of bidirectional associative memory neural networks with time delays
Physics Letters A
LMI-based criteria for global robust stability of bidirectional associative memory networks with time delay
Nonlinear Analysis
Cited by (185)
Finite-time event-triggered approach for recurrent neural networks with leakage term and its application
2021, Mathematics and Computers in SimulationSynchronization control of neutral-type neural networks with sampled-data via adaptive event-triggered communication scheme
2021, Journal of the Franklin InstituteNon-fragile state estimation for fractional-order delayed memristive BAM neural networks
2019, Neural NetworksCitation Excerpt :About three decades ago, Kosko firstly introduced and studied bidirectional associative memory (BAM) networks, which were two-layer heteroassociative networks (Kosko, 1987, 1988). Since then, BAM neural networks were paid noticeable attention due to their extensive applications in image and signal processing, pattern recognition and artificial intelligence, and so on (Cao & Wan, 2014; Mathiyalagan, Park, & Sakthivel, 2015; Park, Park, Kwon, & Lee, 2008; Wang, Tian and Zhen, 2018; Wang, Yang, Xu, & Li, 2017; Xu & Li, 2018; Zhu & Cao, 2012). The first memristor device was invented by HP group (Strukov, Snider, Stewart, & Williams, 2008; Tour & He, 2008), which confirmed Leno Chua’s prediction is correct (Chua, 1971).
New approaches to stability analysis for time-varying delay systems
2019, Journal of the Franklin Institute