On the Geometry of Deep Learning
Year: 2024
Type: preprint
Abstract: In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function approximation by affine splines (continuous piecewise linear functions in multiple dimensions). In particular, we will overview work over the past decade on understanding certain geometrical properties of a deep network's affine spline mapping, in particular how it tessellates its input space. As we will see, the affine spline connection and geometrical viewpoint provide a powerful portal through which to view, analyze, and improve the inner workings of a deep network.
Source: arXiv (Cornell University)
Authors: Balestriero, Randall, Humayun, Ahmed Imtiaz, Baraniuk, Richard
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6910648627
Cites:
Cited by:
Related to: