Nicola Quercioli: Group equivariant non-expansive operators for data analysis and machine learning
Tid: Må 2019-12-02 kl 15.15 - 16.15
Plats: KTH, F11
Föreläsare: Nicola Quercioli, University of Bologna
In this talk we will introduce a general mathematical framework for group equivariance in the machine learning context. The framework builds on a synergy between persistent homology and the theory of group actions. Our focus will be on showing the topological and metric properties of the space of group equivariant non-expansive operators (GENEOs), which are maps between function spaces associated with groups of transformations.