Conférence "Cross-domain transfer in humans and machines"

  • Recherche
  • International
Publié le 20 janvier 2025 Mis à jour le 20 janvier 2025
Date(s)

le 23 janvier 2025

14h00
Lieu(x)

Campus Saint Jean d'Angely

Salle de conférence 031
illustration axe 1
illustration axe 1

23/01/2025. Dans le cadre du projet de recherche "Analogic-Mapping" soutenu par l'axe 1, Leonidas Alex Doumas de l'Université d'Édimbourg (The University of Edinburgh) donne une conférence en anglais sur la cartographie analogique.

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"

Photo Leonidas Doumas
Photo Leonidas Doumas