YoVDO

Inverse Problems on Graphs with Geometric Deep Learning

Offered By: APS Physics via YouTube

Tags

Graph Theory Courses Particle Physics Courses Computational Statistics Courses Non-Euclidean Geometry Courses Geometric Deep Learning Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore geometric deep learning applied to inverse problems on graphs in this 33-minute conference talk from the 2018 Physics Next workshop. Delve into topics like non-Euclidean geometries, physics-based geometric learning, and graph neural networks. Learn how these techniques are applied to particle physics, neutrino detection, and community detection. Discover the latest developments in computational-to-statistical gaps and supervised community detection, and gain insights into current challenges and open problems in the field.

Syllabus

Intro
DEEP LEARNING ON REGULAR GRIDS
TOWARDS NON-EUCLIDEAN GEOMETRIES
PHYSICS-BASED GEOMETRIC LEARNING
GEOMETRIC STABILITY IN EUCLIDEAN DOMAINS
CONVOLUTIONAL NEURAL NETWORKS
NON-EUCLIDEAN GEOMETRIC STABILITY
DEFORMATIONS AND METRICS
DIFFUSION AND METRIC STABILITY
LINEAR STABLE GENERATORS
LAPLACIAN INTERPRETATION
SURFACE REPRESENTATIONS
PARTICLE PHYSICS WITH GRAPH NEURAL NETWORKS
ICECUBE NEUTRINO DETECTION
INVERSE PROBLEMS ON GRAPHS
DABL-DRIVEN COMMUNITY DETECTION
REACHING DETECTION THRESHOLD ON SEM
GRAPH NEURAL NETWORKS ON GRAPH HIERARCHES
COMPUTATIONAL-TO-STATISTICAL GAPS
SUPERVISED COMMUNITY DETECTION
CURRENT AND OPEN PROBLEMS


Taught by

APS Physics

Related Courses

History of Non-Euclidean Geometry
Extra Credits via YouTube
Cool Math Series
YouTube
Preparing for Further Study in Mathematics
Manchester Grammar School via FutureLearn
An Introduction to Hyperbolic Geometry
Indian Institute of Technology Kanpur via Swayam
A Brief History of Geometry III - The 19th Century - Sociology and Pure Mathematics
Insights into Mathematics via YouTube