LEARNING NONOVERLAPPING PERCEPTRON NETWORKS FROM EXAMPLES AND MEMBERSHIP QUERIES

We investigate, within the PAC learning model. the problem of learning nonoverlapping perceptron networks (also known as read-once formulas over a weighted threshold basis). These are loop-free neural nets in w hich each node has only one outgoing weight. We give a polynomial time algorithm that PAC learns any nonovelapping perceptron network using examples and membership queries. The algorithm is able to identify bot h the architecture and the weight values necessary to represent the fu nction to be learned. Our results shed some light on the effect of the overlap on the complexity of learning in neural networks.