Geometric Deep Learning is an attempt for geometric unification of a broad class of ML problems from the perspectives of symmetry and invariance. These principles not only underlie the breakthrough performance of convolutional neural networks and the recent success of graph neural networks but also provide a principled way to construct new problem-specific neural network architectures. In this seminar, I will overview the mathematical principles underlying Geometric Deep Learning on grids, graphs, and manifolds, and show some of the exciting applications of these methods in the domains of computer vision, social science, biology, and drug design.