Conférence "Cross-domain transfer in humans and machines"

Titre de la conférence :

"Cross-domain transfer in humans and machines"
 

Résumé :

Recent advances in deep learning have produced models that far outstrip human performance in a number of domains. However, where machine learning approaches still fall far short of human-level performance is in the capacity to transfer knowledge across domains. While a human learner will happily apply knowledge acquired in one domain (e.g., mathematics) to a different domain (e.g., cooking; a vinaigrette is really just a ratio between edible fat and acid), machine learning models still struggle profoundly at such tasks. I will present a case that human intelligence might be (at least partially) usefully characterised by our ability to transfer knowledge widely, and a framework that we have developed for learning representations that support such transfer. The model is compared to a current machine learning approaches.
 

Intervenant :

Leonidas Alex DOUMAS travaille dans le domaine de la modulation informatique et des neurosciences cognitives à l'Université d'Édimbourg, en Écosse.
Parmi ses publications : "A Theory of Relation Learning and Cross-Domain Generalization"