Seminar iz veštačke inteligencije, 28. april 2021.

Naredni sastanak Seminara biće održan onlajn u sredu, 28. aprila 2021. od 19 do 20 časova.

Predavač: dr Petar Veličković, Senior Research Scientist at DeepMind

Naslov predavanja: GEOMETRIC DEEP LEARNING: GRIDS, GRAPHS, GROUPS, GEODESICS AND GAUGES

Apstrakt:
The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach –such as computer vision, playing Go, or protein folding – are in fact feasible with appropriate computational scale. Remarkably, the essence of deep learning is built from two simple algorithmic principles: first, the notion of representation or feature learning, whereby adapted, often hierarchical, features capture the appropriate notion of regularity for each task, and second, learning by local gradient-descent type methods, typically implemented as backpropagation.

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. This talk is concerned with exposing these regularities through unified geometric principles that can be applied throughout a wide spectrum of applications.

Such a ‘geometric unification’ endeavour in the spirit of Felix Klein's Erlangen Program serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented.

Napomena:
Registraciona forma za učesće i link za pristup predavanju ako ste već registrovani:
https://miteam.mi.sanu.ac.rs/asset/CW5nJWDSEZDj7p32p

Ukoliko želite samo da gledate predavanje bez mogućnosti aktivnog učešća, prenos će biti dostupan na sledećem linku:
https://miteam.mi.sanu.ac.rs/asset/4LNW8WtML7rLKojoz


 Ostavite vaš komentar 

Komentari(0)

Nažalost nije moguće ostaviti komentar.