Titre:
  • Fast Search for Small and Efficient Neural Network Architectures through In-Supervised Learning
Auteur:García-Díaz, Antonio
Président du jury:Sacharidis, Dimitrios
Promoteur:Bersini, Hugues
Membre du jury:Debeir, Olivier; Bontempi, Gianluca; Heinrich, Mary Katherine; Macq, Benoît; Mancas, Matei MM
Informations sur la publication:Université libre de Bruxelles, Ecole polytechnique de Bruxelles – Informatique, Bruxelles
Date de défense:2023-11-10
Sujet CREF:Intelligence artificielle
Informatique mathématique
Informatique générale
Volumes/pages:250 p.
Mots-clés:DensEMANN
DenseNet
EMANN
In-supervised
Neural architecture search
NAS
Growing
Constructing
Pruning
Sparsification
Connection strength
Intitulé du diplôme:Doctorat en Sciences de l'ingénieur et technologie
Note générale:In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of the Université libre de Bruxelles’ products or services. Internal or personal use of this material is permitted. If interested in reprinting/republishing IEEE copyrighted material for advertising or promotional purposes or for creating new collective works for resale or redistribution, please go to http://www.ieee.org/publications_standards/publications/rights/rights_link.html to learn how to obtain a License from RightsLink. If applicable, University Microfilms and/or ProQuest Library, or the Archives of Canada may supply single copies of the dissertation.
Langue:Anglais
Anneé académique:2023-2024