Human-level concept learning through probabilistic program induction
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
People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms-for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world's alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches. We also present several "visual Turing tests" probing the model's creative generalization abilities, which in many cases are indistinguishable from human behavior.
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
- Science
- Thématique
- Machine Learning and Algorithms
- Domaine
- Computer Science
- Établissements canadiens
- Canada Research ChairsUniversity of Toronto
- Organismes subventionnaires
- Army Research OfficeOffice of Naval ResearchNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
- Mots-clés
- Computer scienceAlphabetArtificial intelligenceProbabilistic logicTuringNatural language processingMachine learningProgramming languageLinguistics
- Résumé présent dans OpenAlex
- oui