A Fast Learning Algorithm for Deep Belief Nets
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.
Résumé
We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.
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
- Neural Computation
- Thématique
- Domain Adaptation and Few-Shot Learning
- Domaine
- Computer Science
- Établissements canadiens
- University of Toronto
- Organismes subventionnaires
- Natural Sciences and Engineering Research Council of CanadaCanada Research ChairsCanadian Institute for Advanced Research
- Mots-clés
- Computer scienceAssociative propertyPrior probabilityDiscriminative modelGenerative modelContent-addressable memoryArtificial intelligenceInferenceAlgorithmGenerative grammarPattern recognition (psychology)Deep belief networkArtificial neural networkMathematicsBayesian probability
- Résumé présent dans OpenAlex
- oui