Graphs in Deep Learning: Applications and Techniques

Related lectures (28)

Page 2 of 3

Introduces the basics of graphs and networks, covering definitions, paths, trees, flows, circulation, and spanning trees.

Explores handling network data, including types of graphs, real-world network properties, and node importance measurement.

Covers linear transformations, matrices, kernels, and properties of invertible matrices.

Explores automorphism groups in trees and graphs, focusing on ends and types of automorphisms.

Explores expanders, Ramanujan graphs, eigenvalues, Laplacian matrices, and spectral properties.

Covers the basics of graph algorithms, focusing on modeling and representation of graphs in memory.

Explores automorphism groups of trees and graphs, including actions on trees and group homomorphisms.

Explores partial derivatives and their role in determining tangents to graphs.

Covers supervised and unsupervised learning techniques in machine learning, highlighting their applications in finance and environmental analysis.

Explores derivatives, tangents, and elementary function rules in general mathematics.