Na FRI bomo gostili Petarja Veličkovića iz podjetja Google DeepMind. Vljudno vabljeni na predavanji, ki bosta, v torek 21. maja 2024, ob 10.00 in 11.30 na FRI (predavalnica bo izbrana naknadno glede na prijave).

Prosimo, prijavite se preko spletnega obrazca, da bomo lahko izbrali ustrezno predavalnico in vas o tem obvestili.

10:00 - 11:15 Geometric Deep Learning

While learning generic functions in high dimensions is a cursed estimation problem, most tasks of interest are not generic, and come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world.

Exploiting the known symmetries of a large system is a powerful and classical remedy against the curse of dimensionality, and forms the basis of most physical theories. Deep learning systems are no exception.

11:30 - 13:00 Categorical Deep Learning

One of the most coveted aims of deep learning theory is to provide a guiding framework from which all neural network architectures can be principally and usefully derived. Moreover, such a framework must generalise both group theory and functional programming — and a natural candidate for achieving this is category theory.

O predavatelju:

Petar Veličković is a staff research scientist at Google DeepMind, an affiliated lecturer at the University of Cambridge, and an associate of Clare Hall, Cambridge. He holds a PhD in computer science from the University of Cambridge (Trinity College), obtained under the supervision of Pietro Liò. He is recognised as an ELLIS Scholar in the Geometric Deep Learning Program.