Sorry, you need to enable JavaScript to visit this website.

Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations

DOI:
10.60864/7qk3-3657
Citation Author(s):
Submitted by:
Landon Butler
Last updated:
6 June 2024 - 10:50am
Document Type:
Poster
 

In this paper we discuss the results recently published in [1] about algebraic signal models (ASMs) based on non commutative algebras and their use in convolutional neural networks. Relying on the general tools from algebraic signal processing (ASP), we study the filtering and stability properties of non commutative convolutional filters. We show how non commutative filters can be stable to small perturbations on the space of operators. We also show that although the spectral components of the Fourier representation in a non commutative signal model are associated to spaces of dimension larger than one, there is a trade-off between stability and selectivity similar to that observed for commutative models. Our results have direct implications for group neural networks, multigraph neural networks and quaternion neural networks, among other non commutative architectures. We conclude by corroborating these results through numerical experiments.

up
0 users have voted: