Estimates of Model Complexity in Neural-Network Learning

Authors: Věra Kůrková
Publication year: 2009
Publication type: Kapitola v monografii
Periodical: Innovations in Neural Information Paradigms and Applications
Projects: Centre for Applied Cybernetics
Bibliographic citation: KŮRKOVÁ, Věra. Estimates of Model Complexity in Neural-Network Learning. In: BIANCHINI, M., MAGGINI, M., SCARSELLI, F., JAIN, L.C, eds. Innovations in Neural Information Paradigms and Applications. Berlin: Springer, 2009, S. 97-111. Studies in Computational Intelligence, 247. ISBN 978-3-642-04002-3
Dostupné z: doi:10.1007/978-3-642-04003-0_5
DOI: 10.1007/978-3-642-04003-0_5
ID: 328492

Abstract

Model complexity in neural-network learning is investigated using tools from nonlinear approximation and integration theory. Estimates of network complexity are obtained from inspection of upper bounds on convergence of minima of error functionals over networks with an increasing number of units to their global minima. The estimates are derived using integral transforms induced by computational units. The role of dimensionality of training data defining error functionals is discussed.