Optimizing Time–multiplexing Raster Cellular Neural  Network simulator using genetic algorithms with  RK8(6)

O. H. Abdelwahed; M. El-Sayed Wahed; O. Mohamed Eldaken

Volume : III, Issue : VI, June - 2013

Optimizing Time–multiplexing Raster Cellular Neural Network simulator using genetic algorithms with RK8(6)

O. H. Abdelwahed, M. El Sayed Wahed, O. Mohamed Eldaken

Abstract :

In this research, a versatile algorithm for simulating CNN arrays and time multiplexing is implemented using numerical integration algorithms; RK4(2), RK4(3) and RK8(6) and. The approach, time–multiplexing simulation, plays a pivotal role in the area of simulating hardware models and testing hardware implementations of CNN. Owing to hardware limitations in practical sense, it is not possible to have a one–one mapping between the CNN hardware processors and all the pixels of the image. 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 presents proper CNN templates for edge detection in image processing. Training of CNN is done by using genetic algorithm