A Sheaf-based Approach to Graph Neural Networks
Offered By: Applied Algebraic Topology Network via YouTube
Course Description
Overview
Explore a sheaf-theoretic perspective on Geometric Deep Learning with a focus on Graph Neural Networks. Delve into the limitations of purely geometric approaches when dealing with non-Euclidean data structures, particularly graphs. Examine how sheaf theory provides a more suitable abstraction for understanding and developing novel Graph Neural Network models. Learn about the intersection of applied algebraic topology and deep learning, gaining insights into advanced techniques for analyzing and processing complex data structures beyond traditional Euclidean spaces.
Syllabus
Cristian Bodnar (11/7/23): A Sheaf-based Approach to Graph Neural Networks
Taught by
Applied Algebraic Topology Network
Related Courses
Making Up Our MindsModels of Consciousness Conferences via YouTube Sheaves as Computable and Stable Topological Invariants for Datasets
Applied Algebraic Topology Network via YouTube Sheaf Based Modeling of Wireless Communications
Applied Algebraic Topology Network via YouTube Exemplars of Sheaf Theory in TDA
Applied Algebraic Topology Network via YouTube Modeling Shapes and Fields - A Sheaf Theoretic Perspective
Applied Algebraic Topology Network via YouTube