|Title||EXPONENTIAL APPROXIMATION OF SOLUTIONS OF BIDIRECTIONAL NEURAL NETWORKS MODEL WITH POSITIVE DELAY|
|Publication Type||Journal Article|
|Year of Publication||2018|
|Authors||ABBAS SYED, CORONEL ANIBAL, PINTO MANUEL, TYAGI SWATI|
|Journal||Neural, Parallel, and Scientific Computations|
|Keywords||approximate solution, delay differential equation, neural networks, piecewise constant argument of generalized type|
In this paper, a class of bidirectional neural network containing delay has been studied. Based on the theory of differential calculus and the generalized Gronwall inequality, the solution of the corresponding neural network model is approximated using discretization method and a sufficient condition is established for its stability. Some easily verifiable sufficient conditions are obtained ensuring that every solution of the discrete-time analogue converges exponentially to the unique solution. In the last section, two numerical example are also presented to validate the feasibility of the proposed results and illustrate the advantages of the discrete-time analogues in numerically simulating the continuous-time networks.