Strobl24

More on Harmonic Analysis

June 9th - 15th 2024

Strobl, AUSTRIA

"Scattering Transform on non abelian finite groups"

Arias Noguerales, Maria Teresa

Scattering Networks were initially designed to elucidate the behavior of early layers in Convolutional Neural Networks (CNNs) over Euclidean spaces and are grounded in wavelets. In this work, we introduce a scattering transform on an arbitrary finite group (not necessarily abelian) within the context of group equivariant convolutional neural networks (G-CNNs). We present wavelets on finite groups and analyze their similarity to classical wavelets. We demonstrate that any feature generated by such a network is stable under the group's action and Lipschitz continuous. Furthermore, we provide computational examples illustrating the application of the scattering transform to analyze data with domains involving non abelian groups. Joint work with Davive Barbieri and Eugenio Hernández.

« back