Vorträge und Posterpräsentationen (ohne Tagungsband-Eintrag):
A. Ipp, M. Favoni, D. Mueller, D. Schuh:
"Preserving lattice gauge equivariance in neural networks";
Vortrag: Heidelberg Stavanger Lattice & Machine Learning Seminar,
Heidelberg and Stavanger (online) (eingeladen);
07.04.2021.
Kurzfassung englisch:
In this talk I report on our recent proposal [1] of Lattice gauge equivariant Convolutional Neural Networks (L-CNNs). These networks preserve gauge symmetry by construction and can therefore serve as a basis for generic machine learning applications on lattice gauge theoretical problems. We demonstrate that L-CNNs can outperform traditional convolutional neural networks in selected applications.
[1] https://arxiv.org/abs/2012.12901
Zugeordnete Projekte:
Projektleitung Gerhard Kahl:
Glasma-ML
Projektleitung Anton Rebhan:
Doktoratskolleg Particles and Interactions
Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.