Symmetry meets AI

Abstract

We explore whether Neural Networks (NNs) can {\it discover} the presence of symmetries as they learn to perform a task. For this, we train hundreds of NNs on a {\it decoy task} based on well-controlled Physics templates, where no information on symmetry is provided. We use the output from the last hidden layer of all these NNs, projected to fewer dimensions, as the input for a symmetry classification task, and show that information on symmetry had indeed been identified by the original NN without guidance. As an interdisciplinary application of this procedure, we identify the presence and level of symmetry in artistic paintings from different styles such as those of Picasso, Pollock and Van Gogh.

8 pages, 8 figures

Cited by in corpus (12)

• Machine Learning and LHC Event Generation
• Event Generators for High-Energy Physics Experiments
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Calomplification -- The Power of Generative Calorimeter Models
• Symmetries, Safety, and Self-Supervision
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Data-Directed Search for New Physics based on Symmetries of the SM
• Discovering Sparse Representations of Lie Groups with Machine Learning
• Data-driven discovery of self-similarity using neural networks
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• Machine learning a manifold