ON GENERALIZATION BY NEURAL NETWORKS

We report new results on the corner classification approach to trainin g feedforward neural networks. It is shown that a prescriptive learnin g procedure where the weights are simply read off based on the trainin g data can provide good generalization. The paper also deals with the relations between the number of separable regions and the size of the training set for a binary data network. Prescriptive learning can be p articularly valuable for real-time applications. (C) 1998 Elsevier Sci ence Inc. All rights reserved.