Results on the use of group equivariant non-expansive operators
for topological data analysis and geometric deep learning
Title
Results on the use of group equivariant non-expansive operators
Speaker
Patrizio Frosini - Università di Bologna
Abstract
Group equivariant non-expansive operators (GENEOs) have been recently introduced as mathematical tools for approximating data observers, when data are represented by real- valued or vector-valued functions. The use of these operators is based on the assumption that the interpretation of data depends on the geometric properties of the observers. In this talk we will illustrate some recent results in the theory of GENEOs, showing how these operators could be used for topological data analysis and geometric deep learning.
Bio
Patrizio Frosini received the PhD degree in Mathematics from the University of Florence (Italy) in 1991. He is currently an associate professor of geometry at the Department of Mathematics of the University of Bologna. In the 90s he introduced the first concepts on which topological persistence and multiparameter topological persistence were subsequently built. He is mainly interested in the connections between Topological Data Analysis and Geometric Deep Learning.
When
April 11th 2022, 15:00
Where
Room 706, UniGe DIMA, Via Dodecaneso 35, Genova, Italy.
Streaming will be available at the link below.