%I Springer
%X The technique known as ?weight decay? in the literature about learning from data is investigated using tools from regularization theory. Weight-decay regularization is compared with Tikhonov?s regularization of the learning problem and with a mixed regularized learning technique. The accuracies of suboptimal solutions to weight-decay learning are estimated for connectionistic models with a-priori fixed numbers of computational units.
%T The Weight-Decay Technique in Learning from Data: An Optimization Point of View
%P 53-79
%K Learning from data; Regularization; Weight decay; Suboptimal solutions; Rates of convergence
%J Computational Management Science
%R 10.1007/s10287-008-0072-5
%D 2009
%V 6
%A Giorgio Gnecco
%A Marcello Sanguineti
%L eprints1796
%N 1