MétaCan
← tous les travaux

Greedy Layer-Wise Training of Deep Networks

2007· book-chapter· en· 4 704 citations· W2110798204 sur OpenAlex· 10.7551/mitpress/7503.003.0024

Pourquoi ce travail est-il dans la base ?

Une base qui oublie comment elle a trouvé un travail ne peut pas être vérifiée. Voici les voies qui ont admis celui-ci.

Affiliation canadienneUne personne signataire a déclaré un établissement canadien. C'est la seule voie dont dispose la base habituelle.

Résumé

Complexity theory of circuits strongly suggests that deep architectures can be much more efficient (sometimes exponentially) than shallow architectures, in terms of computational elements required to represent some functions. Deep multi-layer neural networks have many levels of non-linearities allowing them to compactly represent highly non-linear and highly-varying functions. However, until recently it was not clear how to train such deep networks, since gradient-based optimization starting from random initialization appears to often get stuck in poor solutions. Hinton et al. recently introduced a greedy layer-wise unsupervised learning algorithm for Deep Belief Networks (DBN), a generative model with many layers of hidden causal variables. In the context of the above optimization problem, we study this algorithm empirically and explore variants to better understand its success and extend it to cases where the inputs are continuous or where the structure of the input distribution is not revealing enough about the variable to be predicted in a supervised task. Our experiments also confirm the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a region near a good local minimum, giving rise to internal distributed representations that are high-level abstractions of the input, bringing better generalization.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.

La notice

Revue
The MIT Press eBooks
Thématique
Generative Adversarial Networks and Image Synthesis
Domaine
Computer Science
Établissements canadiens
Université de Montréal
Organismes subventionnaires
Mots-clés
Training (meteorology)Layer (electronics)Computer scienceArtificial intelligenceGeographyMaterials scienceComposite materialMeteorology
Résumé présent dans OpenAlex
oui