A study of artificial neural networks and their learning algorithms

The work presented in this thesis is mainly involved in the study of Artificial Neural Networks (ANNs) and their learning strategies. The ANN simulator incorporating the Backpropagation (BP) algorithm is designed and analysed and run on a MIMD parallel computer namely the Balance 8000 multiprocessor machine. Initially, an overview of the learning algorithms of ANNs are described. Some of the acceleration techniques including Heuristic methods for the BP like algorithms are introduced. The software design of the simulator for both On-line and Batch BP is described. Two different strategies for parallelism are considered and the results of the speedups of both algorithms are compared. Later a Heuristic algorithm (GRBH) for accelerating the BP method is introduced and the results are compared with the BP using a variety of expositing examples. The simulator is used to train networks for invariant character recognition using moments. The trained networks are tested for different examples and the results are analysed. The thesis concludes with a chapter summarizing the main results and suggestions for further study.