eprintid: 1708
rev_number: 8
eprint_status: archive
userid: 46
dir: disk0/00/00/17/08
datestamp: 2013-09-13 09:25:57
lastmod: 2013-09-16 12:03:00
status_changed: 2013-09-13 09:25:57
type: article
metadata_visibility: no_search
creators_name: Gnecco, Giorgio
creators_name: Sanguineti, Marcello
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
title: The weight-decay technique in learning from data: an optimization point of view
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: Learning from data; Regularization; Weight decay; Suboptimal solutions; Rates of convergence
abstract: 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.
date: 2009
date_type: published
publication: Computational Management Science
volume: 6
number: 1
publisher: Springer
pagerange: 53-79
id_number: 10.1007/s10287-008-0072-5
refereed: TRUE
issn: 1619-697X
official_url: http://dx.doi.org/10.1007/s10287-008-0072-5
projects: Partially supported by a PRIN grant from the Italian Ministry for University and Research, project “Models and Algorithms for Robust Network Optimization”.
citation:   Gnecco, Giorgio and Sanguineti, Marcello  The weight-decay technique in learning from data: an optimization point of view.  Computational Management Science, 6 (1).  pp. 53-79.  ISSN 1619-697X      (2009)