Tracked shipping to South Africa with premium packaging for just R199 

Ship to
South Africa
0

My Account

  • argentina
  • chile
  • colombia
  • españa
  • méxico
  • perú
  • estados unidos
  • internacional

menu

Select your country

Americas

Europe

Rest of the world

portada Equivariant & Coordinate Independent Convolutional Networks
Type
Physical Book
Publisher
Author
Language
English
Pages
592
Format
Hardcover
Dimensions
22.9x15.2x3.2 cm
ISBN13
9789819806621

Equivariant & Coordinate Independent Convolutional Networks

Weiler Maurice (Author) · World Scientific Publishing Company · Hardcover

Equivariant & Coordinate Independent Convolutional Networks - Weiler Maurice

Cheaper New Book Imported to South Africa
Delivery: 20 Oct - 02 Nov Shipping: 15 to 19 business days.
R 4,009
Faster New Book Imported to South Africa
Delivery: 07 Oct - 15 Oct Shipping: 6 to 7 business days.
R 4,355
R 4,009

Choose the list to add your product or create one New List

Go to My Wishlists
Calculate shipping cost

Synopsis "Equivariant & Coordinate Independent Convolutional Networks"

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.Equivariant networks commute with actions of some symmetry group on their feature spaces. The relevant group actions in this work are geometric transformations of feature fields, like translations, rotations, or reflections of images. Equivariant models generalize everything they learn over the considered group of transformations. This property makes them significantly more data efficient, interpretable, and robust in comparison to non-equivariant models.Convolutional Neural Networks (CNNs) are the most common network architecture for processing feature fields. Conventional CNNs operate on Euclidean spaces and are translation equivariant, i.e. position independent. This work explains how to extend CNNs to be equivariant under more general symmetries of space.Coordinate independence: Manifolds are in general not equipped with a canonical choice of coordinates. Feature fields and neural network layers are hence required to be coordinate independent, that is, expressible relative to different frames of reference. The ambiguity of local frames represents the gauge freedom of our neural field theory. We show that the demand for coordinate independence requires CNNs to be equivariant under local gauge transformations.

Customers reviews

More customer reviews
  • 0% (0)
  • 0% (0)
  • 0% (0)
  • 0% (0)
  • 0% (0)

Frequently Asked Questions about the Book

Is the book original?

All books in our catalog are Original.

In what language is the book written?

The book is written in English.

What is the format of this book?

The binding of this edition is Hardcover.

Questions and Answers about the Book

Do you have a question about the book? Login to be able to add your own question.

Opinions about Bookdelivery

More customer reviews