<div class="csl-bib-body">
<div class="csl-entry">Schuh, D., Ipp, A., Müller, D., Aronsson, J., & Favoni, M. (2023, June 27). <i>Global and local symmetries in neural networks</i> [Conference Presentation]. Machine learning for lattice field theory and beyond 2023, Trento, Italy. http://hdl.handle.net/20.500.12708/191736</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/191736
-
dc.description.abstract
Incorporating symmetries into neural network architectures has become increasingly popular. Convolutional Neural Networks (CNNs) leverage the assumption of global translational symmetry in the data to ensure that their predicted observable transforms properly under translations. Lattice gauge equivariant Convolutional Neural Networks (L-CNNs) [1] are designed to respect local gauge symmetry, which is an essential component in lattice gauge theories. This property makes them effective in approximating gauge covariant functions on a lattice. Since many observables exhibit additional global symmetries to translations, an extension of the L-CNN to a more general symmetry group, including e.g. rotations and reflections [2], is desirable.
In this talk, I will present some of the essential L-CNN layers and motivate why they can approximate gauge equivariant functions on a lattice. I will comment on the robustness of such a network against adversarial attacks along gauge orbits in comparison to a traditional CNN. Then, I will provide a geometric formulation of L-CNNs and show how convolutions in L-CNNs arise as a special case of gauge equivariant neural networks on SU(N) principal bundles. Finally, I will discuss how the L-CNN layers can be generalized to respect global rotations and reflections in addition to translations.
[1] M. Favoni, A. Ipp, D. I. Müller, D. Schuh, Phys. Rev. Lett. 128 (2022), 032003, [arXiv:2012.12901]
[2] J. Aronsson, D. I. Müller, D. Schuh [arXiv:2303.11448]
en
dc.language.iso
en
-
dc.subject
Symmetry
en
dc.subject
Neural Networks
en
dc.subject
Machine Learning
en
dc.title
Global and local symmetries in neural networks
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.contributor.affiliation
Chalmers University of Technology, Sweden
-
dc.type.category
Conference Presentation
-
tuw.publication.invited
invited
-
tuw.researchTopic.id
C5
-
tuw.researchTopic.name
Computer Science Foundations
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E136 - Institut für Theoretische Physik
-
tuw.author.orcid
0000-0001-7602-2503
-
tuw.author.orcid
0000-0001-9511-3523
-
tuw.author.orcid
0000-0002-8163-7614
-
tuw.author.orcid
0000-0001-7912-1857
-
tuw.event.name
Machine learning for lattice field theory and beyond 2023
