Relocation of compact sets in R n by diffeomorphisms and linear separability of datasets in R n
The discussion of the paper 'Relocation of compact sets in R n by diffeomorphisms and linear separability of datasets in R n ' covers methods for manipulating complex data. Hosts explore how to theoretically move entire collections of data using smooth transformations (diffeomorphisms) and how to practically implement this using specific Deep Neural Network architectures. The tangled or complex data is solved by lifting it into higher dimensions.