This paper discusses the aims of automatic character recognition and the challenges that arabic characters pose to the implementation of a recognition system suitable for this script. The role of neural networks used as classifiers is examined, several neural network architectures are investigated, and their classification performance is evaluated when trained and tested with handwritten Arabic characters without preprocessing or feature extraction. Of the networks implemented, best classification performance was provided by a 2-layer (1 hidden, 1 output layer) network using backpropagation with momentum.