Can I read A Theory of Hyperbolic Prototype Learning on EtoBox?

A Theory of Hyperbolic Prototype Learning by Keller-Ressel, Martin is a scholarly article available to read on EtoBox.

What is A Theory of Hyperbolic Prototype Learning about?

We introduce Hyperbolic Prototype Learning, a type of supervised learning, where class labels are represented by ideal points (points at infinity) in hyperbolic space. Learning is achieved by minimizing the 'penalized Busemann loss', a new loss function based on the Busemann function of hyperbolic geometry. We discuss several theoretical features of this setup. In particular, Hyperbolic Prototype Learning becomes equivalent to logistic regression in the one-dimensional case.

Author

Keller-Ressel, Martin

Published

2020

Language

EN