Beiträge in Tagungsbänden:
A. Ipp, D. Mueller, M. Favoni, D. Schuh:
"Preserving gauge invariance in neural networks";
in: "A Virtual Tribute to Quark Confinement and the Hadron Spectrum (vConf21)",
258;
EPJ Web of Conferences,
2022,
ISSN: 2100-014x,
Paper-Nr. 09004,
8 S.
Kurzfassung englisch:
In these proceedings we present lattice gauge equivariant convolutional neural networks (L-CNNs) which are able to process data from lattice gauge theory simulations while exactly preserving gauge symmetry. We review aspects of the architecture and show how L-CNNs can represent a large class of gauge invariant and equivariant functions on the lattice. We compare the performance of L-CNNs and non-equivariant networks using a non-linear regression problem and demonstrate how gauge invariance is broken for non-equivariant models.
"Offizielle" elektronische Version der Publikation (entsprechend ihrem Digital Object Identifier - DOI)
http://dx.doi.org/10.1051/epjconf/202225809004
Zugeordnete Projekte:
Projektleitung Gerhard Kahl:
Glasma-ML
Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.