Abstract
The study of -equivariant operators is of great interest to explain and understand the architecture of neural networks. In this paper we show that each linear -equivariant operator can be produced by a suitable permutant measure, provided that the group transitively acts on a finite signal domain . This result makes available a new method to build linear -equivariant operators in the finite setting.
Connections
Explore this paper’s authors, topics and related work.
Building this map preview
BZPEER is loading the nearby papers, people, topics and institutions for this page.
Reviews 0
Write a review
No reviews yet.
Discussion 0
Add a comment
No comments yet.