Alberto Rossi (DIISM, University of Siena)

May 24, 2018 – 9:30 AM

DIISM, Artificial Intelligence laboratory (room 201), Siena SI

Description

Many research areas deal with structured data, like social science, biology and computer graphics.
Such geometric data could be very large and complex (social network), and machine learning techniques reveal their power to deal with such data.
Deep learning are proved to be very powerful, in a wide range of application, like computer vision, natural language processing and audio analysis, but this power are exploited dealing with problems underlying Euclidean space.
Geometric deep learning exploits different methods to transfer deep learning methods to structured domains data, like graphs and manifolds.

Resources

Geometric Deep Learning Presentation