Unsupervised Layer-Wise Model Selection in Deep Neural Networks

Ludovic Arnold 1, 2 Hélène Paugam-Moisy 3, 2 Michèle Sebag 1, 2
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
3 DM2L - Data Mining and Machine Learning
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remains model selection, e.g. selecting the number of neurons in each DNN layer. The hyper-parameter search space exponentially increases with the number of layers, making the popular grid search-based approach used for finding good hyper-parameter values intractable. The question investigated in this paper is whether the unsupervised, layer-wise methodology used to train a DNN can be extended to model selection as well. The proposed approach, considering an unsupervised criterion, empirically examines whether model selection is a modular optimization problem, and can be tackled in a layer-wise manner. Preliminary results on the MNIST data set suggest the answer is positive. Further, some unexpected results regarding the optimal size of layers depending on the training process, are reported and discussed.
Type de document :
Communication dans un congrès
19th European Conference on Artificial Intelligence (ECAI'10), Aug 2010, Lisbon, Portugal. 2010, 〈10.3233/978-1-60750-606-5-915〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

Contributeur : Ludovic Arnold <>
Soumis le : mardi 1 juin 2010 - 17:34:08
Dernière modification le : mercredi 31 octobre 2018 - 12:24:25
Document(s) archivé(s) le : vendredi 19 octobre 2012 - 15:30:30


Fichiers produits par l'(les) auteur(s)



Ludovic Arnold, Hélène Paugam-Moisy, Michèle Sebag. Unsupervised Layer-Wise Model Selection in Deep Neural Networks. 19th European Conference on Artificial Intelligence (ECAI'10), Aug 2010, Lisbon, Portugal. 2010, 〈10.3233/978-1-60750-606-5-915〉. 〈hal-00488338〉



Consultations de la notice


Téléchargements de fichiers