SciPost Physics

SciPost Phys. 11, 014 (2021) · published 15 July 2021

• doi: 10.21468/SciPostPhys.11.1.014
• pdf
• BiBTeX
• RIS
• Submissions/Reports
• 

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.

• Khosa et al., A simple guide from machine learning outputs to statistical criteria in particle physics
  SciPost Phys. Core 5, 050 (2022) [Crossref]
• Forestano et al., Accelerated discovery of machine-learned symmetries: Deriving the exceptional Lie groups G2, F4 and E6
  Physics Letters B 847, 138266 138266 (2023) [Crossref]
• Butter et al., Machine learning and LHC event generation
  SciPost Phys. 14, 079 (2023) [Crossref]
• Forestano et al., Identifying the group-theoretic structure of machine-learned symmetries
  Physics Letters B 847, 138306 138306 (2023) [Crossref]
• Birman et al., Data-directed search for new physics based on symmetries of the SM
  Eur. Phys. J. C 82, 508 (2022) [Crossref]
• Dillon et al., Symmetries, safety, and self-supervision
  SciPost Phys. 12, 188 (2022) [Crossref]
• Forestano et al., Discovering sparse representations of Lie groups with machine learning
  Physics Letters B 844, 138086 138086 (2023) [Crossref]
• Xie et al., How visual chirality affects the performance of image hashing
  Neural Comput & Applic, (2022) [Crossref]
• Bieringer et al., Calomplification — the power of generative calorimeter models
  J. Inst. 17, P09028 (2022) [Crossref]
• Campbell et al., Event generators for high-energy physics experiments
  SciPost Phys. 16, 130 (2024) [Crossref]
• Gautam et al., Mango Leaf Stress Identification Using Deep Neural Network
  34, 849 (2022) [Crossref]
• Hashemi et al., Deep generative models for detector signature simulation: A taxonomic review
  Reviews in Physics 12, 100092 100092 (2024) [Crossref]
• Forestano et al., Deep learning symmetries and their Lie groups, algebras, and subalgebras from first principles
  Mach. Learn.: Sci. Technol. 4, 025027 (2023) [Crossref]
• Bhattacharya et al.,
  , 01 (2022) [Crossref]
• Barenboim et al., Exploring how a generative AI interprets music
  Neural Comput & Applic 36, 17007 (2024) [Crossref]
• Desai et al., Symmetry discovery with deep learning
  Phys. Rev. D 105, 096031 (2022) [Crossref]
• Roman et al., Oracle-Preserving Latent Flows
  Symmetry 15, 1352 (2023) [Crossref]
• Craven et al., Machine learning a manifold
  Phys. Rev. D 105, 096030 (2022) [Crossref]
• Del Debbio et al., Efficient modeling of trivializing maps for lattice ϕ4 theory using normalizing flows: A first look at scalability
  Phys. Rev. D 104, 094507 (2021) [Crossref]