• Open Daily: 10am - 10pm
    Alley-side Pickup: 10am - 7pm

    3038 Hennepin Ave Minneapolis, MN
    612-822-4611

Open Daily: 10am - 10pm | Alley-side Pickup: 10am - 7pm
3038 Hennepin Ave Minneapolis, MN
612-822-4611
Equivariant & Coordinate Independent Convolutional Networks

Equivariant & Coordinate Independent Convolutional Networks

Hardcover

Series: Progress in Data Science, Book 1

General Mathematics

ISBN10: 9819806623
ISBN13: 9789819806621
Publisher: World Scientific Publishing Company
Published: Jan 15 2026
Pages: 592
Weight: 2.10
Height: 1.25 Width: 6.00 Depth: 9.00
Language: English

What is the appropriate geometric structure for neural networks that process spatial signals on Euclidean spaces or more general manifolds? This question takes us on a journey which leads to a gauge field theory of convolutional networks.

Feature vector fields: The spatial signals we are interested in are fields of feature vectors. Feature fields allow to describe data like images, audio, videos, point clouds, or tensor fields, such as fluid flows and electromagnetic fields.

Also in

General Mathematics