Colloqui
della Classe di Scienze
ore 15.00
Scuola Normale
Superiore
Pisa
(Aula
Mancini)
Nicolò
Cesa-Bianchi
Università
degli Studi di Milano
Terrà un seminario dal
titolo:
“The
game-theoretic approach to machine learning and adaptation.”
Abstract:
The
design of artificial systems able to learn and adapt has been one of the main
goals of Artificial Intelligence since its very beginning. To this end,
statistical modelling has proven to be a tool of extraordinary
effectiveness.
In
some cases, however, statistics is not the most adequate language for analyzing
the interaction between a
learning
agent and an ever-changing environment. Indeed, a research thread, emerged in
parallel with statistical learning, views this interaction as a repeated game
between agent and environment. This different approach allows to analyze, in a
rigorous framework, predictive models without any statistical assumptions. In
this talk we will trace the roots of the game-theoretic approach in learning
theory and describe some of the key results.
Tutti gli
interessati sono invitati a partecipare.