Learning Nonoverlapping Perceptron Networks from Examples and Membership Queries

Authors:
Thomas R. Hancock;Mostefa Golea;Mario Marchand
Affiliations:
Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540. hancock@learning.siemens.com;Ottawa-Carleton Institute for Physics, University of Ottawa, Ottawa, Ont., Canada KIN 6N5. golea@physics.uottawa.ca;Ottawa-Carleton Institute for Physics, University of Ottawa, Ottawa, Ont., Canada KIN 6N5. mario@physics.uottawa.ca
Venue:
Machine Learning
Year:
1994

Citing 0
Cited 6

Average case analysis of the clipped Hebb rule for nonoverlapping perception networks

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
On the Sample Complexity for Nonoverlapping Neural Networks

Machine Learning
Function Decomposition in Machine Learning

Machine Learning and Its Applications, Advanced Lectures
On the Sample Complexity for Neural Trees

ALT '98 Proceedings of the 9th International Conference on Algorithmic Learning Theory
On the complexity of computing and learning with multiplicative neural networks

Neural Computation
Generalization and Selection of Examples in Feedforward Neural Networks

Neural Computation

Quantified Score

Hi-index	0.04

Visualization

Abstract

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 which each node has only one outgoing weight. We give a polynomial time algorithm that PAC learns any nonoverlapping perceptron network using examples and membership queries. The algorithm is able to identify both the architecture and the weight values necessary to represent the function to be learned. Our results shed some light on the effect of the overlap on the complexity of learning in neural networks.