Volume : 2, Issue : 5, May - 2013
Optimizing Single–Layer Raster Cellular Neural Network Simulator Using Simulated Annealing Technique with Rk84(5)
O. H. Abdelwahed, M. El Sayed Wahed
Abstract :
An efficient numerical integration algorithm for single layer Raster Cellular Neural Networks (CNN) simulator is presented in this paper. Explicit Runge{Kutta (RK) methods provide an attractive means for the solution of initial value problems of first–order differential equations in the form of pairs of orders p (p –1). Most existing RK formulas (single methods as well as pairs) use the minimal number of stages required for achieving a prescribed order. In this article we shall study, in terms of efficiency and reliability, RK pairs of orders p (q).The simulator is capable of performing CNN simulations for any size of input image, thus a powerful tool for researchers investigating potential applications of CNN. This paper reports an efficient algorithm exploiting the latency properties of Cellular Neural Networks along with numerical integration techniques; simulation results and comparisons are also presented.
Keywords :
Article:
Download PDF Journal DOI : 10.15373/2249555XCite This Article:
O.H. Abdelwahed, M. El-Sayed Wahed / Optimizing Single-Layer Raster Cellular Neural Network Simulator Using Simulated Annealing Technique with Rk84(5) / Global Journal For Research Analysis, Vol:2, Issue:5 May 2013