https://thegradient.pub/towards-geometric-deep-learning/ Towards Geometric Deep LearningMichael Bronstein18.Feb.2023 “Geometric Deep Learning is an umbrella term for approaches considering a broad class of ML problems from the perspectives of symmetry and invariance.”
What I Read: Neural-Implicit Representations, 3D Shapes
https://towardsdatascience.com/neural-implicit-representations-for-3d-shapes-and-scenes-c6750dff49db?gi=dd4876367dbb Neural-Implicit Representations for 3D Shapes and ScenesOmri KaduriJun 26 “Tracing the progress of deep learning-based solutions to computer graphics tasks”
What I Read: Graph Neural Networks, Differential Geometry, Algebraic Topology
https://towardsdatascience.com/graph-neural-networks-through-the-lens-of-differential-geometry-and-algebraic-topology-3a7c3c22d5f Graph Neural Networks through the lens of Differential Geometry and Algebraic TopologyMichael Bronstein “Differential geometry and algebraic topology are not encountered very frequently in mainstream machine learning… tools from
What I Read: Statistics, Geometry Problem
https://www.quantamagazine.org/statistics-postdoc-tames-decades-old-geometry-problem-20210301/ Statistics Postdoc Tames Decades-Old Geometry ProblemTo the surprise of experts in the field, a postdoctoral statistician has solved one of the most important problems in high-dimensional convex geometry.Erica KlarreichMarch