Título: Introduction to equivariant machine learning
Palestrante: Soledad Villar (Jhons Hopkins, Estados Unidos)
Local: Transmissão On-line.Clique AQUI para acessar. (Sala abre às 14:55h)
Resumo: : There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), scaling (units), and permutations. In this talk we overview different techniques to implement machine learning models that respect these symmetries.