Geometric deep learning is a relatively small but growing field heavily based on group theory and representation theory. My own research on the subject was quite foundational/general and also required differential geometry, gauge theory, harmonic analysis, and functional analysis. Everything centered around equivariance; bulding problem-dependent local/global symmetries into the network architecture in order to make use of weight sharing and reduce the amount of data needed for the network to learn.
Geometric deep learning is a relatively small but growing field heavily based on group theory and representation theory. My own research on the subject was quite foundational/general and also required differential geometry, gauge theory, harmonic analysis, and functional analysis. Everything centered around equivariance; bulding problem-dependent local/global symmetries into the network architecture in order to make use of weight sharing and reduce the amount of data needed for the network to learn.