2012 | OriginalPaper | Buchkapitel
Large Ensemble Averaging
verfasst von : David Horn, Ury Naftaly, Nathan Intrator
Erschienen in: Neural Networks: Tricks of the Trade
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Averaging over many predictors leads to a reduction of the variance portion of the error. We present a method for evaluating the mean squared error of an infinite ensemble of predictors from finite (small size) ensemble information. We demonstrate it on ensembles of networks with different initial choices of synaptic weights. We find that the optimal stopping criterion for large ensembles occurs later in training time than for single networks. We test our method on the suspots data set and obtain excellent results.