LEARNING ALGORITHM EFFECT ON MULTILAYER FEED FORWARD ARTIFICIAL NEURAL NETWORK PERFORMANCE IN IMAGE CODING

One of the essential factors that affect the performance of Artificial NeuralNetworks is the learning algorithm. The performance of Multilayer FeedForward Artificial Neural Network performance in image compression usingdifferent learning algorithms is examined in this paper. Based on GradientDescent, Conjugate Gradient, Quasi-Newton techniques three different errorback propagation algorithms have been developed for use in training two typesof neural networks, a single hidden layer network and three hidden layersnetwork. The essence of this study is to investigate the most efficient andeffective training methods for use in image compression and its subsequentapplications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms.