2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/17238A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their target outputs. For large networks our procedure needs far fewer examples to achieve good generalization than traditional on-line algorithms.5 pages, 3 figures, to appear: Phys. Rev. LettsDisordered Systems and Neural Networkstext