Geometric and Topological deep learning is a project that is aimed at two goals
(1) Introducing topological language to deep learning for the purpose of utilizing the minimal mathematical structures to formalize problems that arise in a generic deep learning problem.
(2) Create, augment and enhance novel deep learning models utilizing the tools available in topology and geometry.
Cell Complex Neural Networks, joint work with Kyle Istvan and Ghada Zamzmi. NeurIPS 2020 Workshop on Topological Data Analysis and Beyond.
A Topological Framework for Deep Learning. Joint work with Kyle Istvan. Under Review.
Simplicial Complex Representation Learning, Joint work with Ghada Zamzmi, and Xuanting Cai