On overfitting, generalization, and randomly expanded training setsOn overfitting, generalization, and randomly expanded training sets Peer-Reviewed Journal Publication Δημοσίευση σε Περιοδικό με Κριτές 2015-10-232000enOutstanding Paper AwardAn algorithmic procedure is developed for the random expansion of a given training set to combat overfitting and improve the generalization ability of backpropagation trained multilayer perceptrons (MLPs). The training set is K-means clustered and locally most entropic colored Gaussian joint input-output probability density function estimates are formed per cluster. The number of clusters is chosen such that the resulting overall colored Gaussian mixture exhibits minimum differential entropy upon global cross-validated shaping. Numerical studies on real data and synthetic data examples drawn from the literature illustrate and support these theoretical developmentsΔημοσίευση σε επιστημονικό περιοδικό http://creativecommons.org/licenses/by/4.0/IEEE Transactions on Neural Networks5111050 - 1057 Karystinos Georgios Καρυστινος Γεωργιος Pados Dimitris A. Institute of Electrical and Electronics Engineers Backpropagation clustering methods entropy Gaussian distributions multilayer perceptrons (MLPs) stochastic approximation stochastic processes