We present a statistical method that exactly learns the class of constant depth μ-perceptron networks with weights taken from {−1, 0 + 1} and arbitrary thresholds when the distribution that generates the input examples is member of the family of product distributions. These networks (also known as nonoverlapping perceptron networks or read-once formulas over a weighted threshold basis) are loop...

In this contribution, one and two-stage neural networks methods for face recognition are presented. For two-stage systems, the Kohonen self-organizing map is used as a feature extractor and multiplayer perceptron (MLP) or radial basis function (RBF) network are used as classifiers. The results of such recognition are compared with face recognition using a one-stage multilayer perceptron and rad...

It is shown that cartesian product and pointwise-sum with a fixed compact set preserve various approximation-theoretic properties. Results for pointwise-sum are proved for F -spaces and so hold for any normed linear space, while the other results hold in general metric spaces. Applications are given to approximation of Lp-functions on the d-dimensional cube, 1 ≤ p < ∞, by linear combinations of...