{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:01:57Z","timestamp":1772604117256,"version":"3.50.1"},"reference-count":57,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T00:00:00Z","timestamp":1686182400000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T00:00:00Z","timestamp":1686182400000},"content-version":"tdm","delay-in-days":7,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"crossref","award":["DE-SC0022148"],"award-info":[{"award-number":["DE-SC0022148"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"Abstract<\/jats:title>We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the symmetry transformations and the corresponding generators. The constructed loss functions ensure that the applied transformations are symmetries and the corresponding set of generators forms a closed (sub)algebra. Our procedure is validated with several examples illustrating different types of conserved quantities preserved by symmetry. In the process of deriving the full set of symmetries, we analyze the complete subgroup structure of the rotation groupsSO<\/jats:italic>(2),SO<\/jats:italic>(3), andSO<\/jats:italic>(4), and of the Lorentz groupS<\/mml:mi>O<\/mml:mi>(<\/mml:mo>1<\/mml:mn>,<\/mml:mo>3<\/mml:mn>)<\/mml:mo><\/mml:math><\/jats:inline-formula>. Other examples include squeeze mapping, piecewise discontinuous labels, andSO<\/jats:italic>(10), demonstrating that our method is completely general, with many possible applications in physics and data science. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.<\/jats:p>","DOI":"10.1088\/2632-2153\/acd989","type":"journal-article","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T22:39:10Z","timestamp":1685140750000},"page":"025027","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Deep learning symmetries and their Lie groups, algebras, and subalgebras from first principles"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0355-2076","authenticated-orcid":false,"given":"Roy T","family":"Forestano","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-9096","authenticated-orcid":true,"given":"Konstantin T","family":"Matchev","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3074-998X","authenticated-orcid":false,"given":"Katia","family":"Matcheva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2719-221X","authenticated-orcid":false,"given":"Alexander","family":"Roman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6683-6463","authenticated-orcid":false,"given":"Eyup B","family":"Unlu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4870-0826","authenticated-orcid":false,"given":"Sarunas","family":"Verner","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"mlstacd989bib1","doi-asserted-by":"publisher","first-page":"14256","DOI":"10.1073\/pnas.93.25.14256","article-title":"The role of symmetry in fundamental physics","volume":"93","author":"Gross","year":"1996","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstacd989bib2","first-page":"pp 501","article-title":"Lectures on Non-supersymmetric BSM Models","author":"Cs\u00e1ki","year":"2018","edition":"ed"},{"key":"mlstacd989bib3","doi-asserted-by":"publisher","DOI":"10.1142\/S0217751X19300199","article-title":"Machine and deep learning applications in particle physics","volume":"34","author":"Bourilkov","year":"2020","journal-title":"Int. J. Mod. Phys. A"},{"key":"mlstacd989bib4","author":"Calafiura","year":"2022"},{"key":"mlstacd989bib5","article-title":"Modern machine learning for LHC physicists","author":"Plehn","year":"2022"},{"key":"mlstacd989bib6","article-title":"Simplifying polylogarithms with machine learning","author":"Dersy","year":"2022"},{"key":"mlstacd989bib7","article-title":"SYMBA: symbolic computation of squared amplitudes in high energy physics with machine learning","author":"Alnuqaydan","year":"2022"},{"key":"mlstacd989bib8","doi-asserted-by":"publisher","first-page":"JHEP08(2011)110","DOI":"10.1007\/JHEP08(2011)110","article-title":"Construction of a kinematic variable sensitive to the mass of the standard model higgs boson in H\u2192WW\u2217\u2192l+\u03bdl\u2212\u03bd\u02c9 using symbolic regression","author":"Choi","year":"2011","journal-title":"J. High Energy Phys. vol."},{"key":"mlstacd989bib9","doi-asserted-by":"publisher","first-page":"eaay2631","DOI":"10.1126\/sciadv.aay2631","article-title":"AI feynman: a physics-inspired method for symbolic regression","volume":"6","author":"Udrescu","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstacd989bib10","article-title":"Deep learning for symbolic mathematics","author":"Lample","year":"2019"},{"key":"mlstacd989bib11","article-title":"Discovering symbolic models from deep learning with inductive biases","author":"Cranmer","year":"2020"},{"key":"mlstacd989bib12","article-title":"Back to the formula\u2014LHC edition","author":"Butter","year":"2021"},{"key":"mlstacd989bib13","article-title":"Accelerating understanding of scientific experiments with end to end symbolic regression","author":"Arechiga","year":"2021"},{"key":"mlstacd989bib14","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3847\/1538-4357\/ac610c","article-title":"Analytical modeling of exoplanet transit spectroscopy with dimensional analysis and symbolic regression","volume":"930","author":"Matchev","year":"2022","journal-title":"Astrophys. J."},{"key":"mlstacd989bib15","article-title":"Deep symbolic regression for recurrent sequences","author":"d\u2019Ascoli","year":"2022"},{"key":"mlstacd989bib16","article-title":"Rediscovering orbital mechanics with machine learning","author":"Lemos","year":"2022"},{"key":"mlstacd989bib17","article-title":"End-to-end symbolic regression with transformers","author":"Kamienny","year":"2022"},{"key":"mlstacd989bib18","article-title":"Symbolic expression transformer: a computer vision approach for symbolic regression","author":"Jiachen","year":"2022"},{"key":"mlstacd989bib19","article-title":"Rethinking symbolic regression datasets and benchmarks for scientific discovery","author":"Matsubara","year":"2022"},{"key":"mlstacd989bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.107.055018","article-title":"Is the machine smarter than the theorist: deriving formulas for particle kinematics with symbolic regression","volume":"107","author":"Dong","year":"2023"},{"key":"mlstacd989bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.010508","article-title":"Discovering physical concepts with neural networks","volume":"124","author":"Iten","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstacd989bib22","doi-asserted-by":"publisher","first-page":"188","DOI":"10.21468\/SciPostPhys.12.6.188","article-title":"Symmetries, safety and self-supervision","volume":"12","author":"Dillon","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstacd989bib23","article-title":"Detecting symmetries with neural networks","author":"Krippendorf","year":"2020"},{"key":"mlstacd989bib24","doi-asserted-by":"publisher","first-page":"028","DOI":"10.21468\/SciPostPhys.5.3.028","article-title":"Deep-learned top tagging with a lorentz layer","volume":"5","author":"Butter","year":"2018","journal-title":"SciPost Phys."},{"key":"mlstacd989bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.121601","article-title":"Equivariant flow-based sampling for lattice gauge theory","volume":"125","author":"Gurtej Kanwar","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstacd989bib26","article-title":"Lorentz group equivariant neural network for particle physics","author":"Bogatskiy","year":"2020"},{"key":"mlstacd989bib27","doi-asserted-by":"publisher","first-page":"JHEP07(2022)030","DOI":"10.1007\/JHEP07(2022)030","article-title":"An efficient Lorentz equivariant graph neural network for jet tagging","author":"Gong","year":"2022","journal-title":"J. High Energy Phys."},{"key":"mlstacd989bib28","article-title":"Symmetry Group Equivariant Architectures for Physics","author":"Bogatskiy","year":"2022"},{"key":"mlstacd989bib29","article-title":"Does Lorentz-symmetric design boost network performance in jet physics?","author":"Congqiao","year":"2022"},{"key":"mlstacd989bib30","article-title":"Lorentz group equivariant autoencoders","author":"Hao","year":"2022"},{"key":"mlstacd989bib31","article-title":"The lie derivative for measuring learned equivariance","author":"Gruver","year":"2022"},{"key":"mlstacd989bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.112008","article-title":"Permutationless many-jet event reconstruction with symmetry preserving attention networks","volume":"105","author":"Fenton","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstacd989bib33","doi-asserted-by":"publisher","first-page":"178","DOI":"10.21468\/SciPostPhys.12.5.178","article-title":"SPANet: generalized permutationless set assignment for particle physics using symmetry preserving attention","volume":"12","author":"Shmakov","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstacd989bib34","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/17\/08\/P08024","article-title":"A method to challenge symmetries in data with self-supervised learning","volume":"17","author":"Tombs","year":"2022","journal-title":"J. Instrum."},{"key":"mlstacd989bib35","article-title":"Using unsupervised learning to detect broken symmetries, with relevance to searches for parity violation in nature (Previously: \u2018Stressed GANs snag desserts\u2019)","author":"Lester","year":"2021"},{"key":"mlstacd989bib36","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1140\/epjc\/s10052-022-10454-2","article-title":"Data-directed search for new physics based on symmetries of the SM","volume":"82","author":"Birman","year":"2022","journal-title":"Eur. Phys. J. C"},{"key":"mlstacd989bib37","article-title":"Lagrangian neural networks","author":"Cranmer","year":"2020"},{"key":"mlstacd989bib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.180604","article-title":"Machine learning conservation laws from trajectories","volume":"126","author":"Liu","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstacd989bib39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1103\/PhysRevE.100.033311","article-title":"Toward an artificial intelligence physicist for unsupervised learning","volume":"100","author":"Tailin","year":"2019","journal-title":"Phys. Rev. E"},{"key":"mlstacd989bib40","doi-asserted-by":"publisher","first-page":"014","DOI":"10.21468\/SciPostPhys.11.1.014","article-title":"Symmetry meets AI","volume":"11","author":"Barenboim","year":"2021","journal-title":"SciPost Phys."},{"key":"mlstacd989bib41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.096030","article-title":"Machine learning a manifold","volume":"105","author":"Craven","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstacd989bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033499","article-title":"Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks","volume":"2","author":"Wetzel","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstacd989bib43","article-title":"Machine learning etudes in conformal field theories","author":"Chen","year":"2020"},{"key":"mlstacd989bib44","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1016\/j.physletb.2017.10.024","article-title":"Machine-learning the string landscape","volume":"774","author":"Yang-Hui","year":"2017","journal-title":"Phys. Lett. B"},{"key":"mlstacd989bib45","doi-asserted-by":"publisher","first-page":"JHEP09(2017)157","DOI":"10.1007\/JHEP09(2017)157","article-title":"Machine learning in the string landscape","author":"Carifio","year":"2017","journal-title":"J. High Energy Phys."},{"key":"mlstacd989bib46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2019.09.005","article-title":"Data science applications to string theory","volume":"839","author":"Ruehle","year":"2020","journal-title":"Phys. Rept."},{"key":"mlstacd989bib47","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.105.096031","article-title":"Symmetry discovery with deep learning","volume":"105","author":"Desai","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstacd989bib48","doi-asserted-by":"publisher","DOI":"10.1016\/j.physletb.2021.136297","article-title":"Machine learning Lie structures & applications to physics","volume":"817","author":"Chen","year":"2021","journal-title":"Phys. Lett. B"},{"key":"mlstacd989bib49","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.180201","article-title":"Machine learning hidden symmetries","volume":"128","author":"Liu","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstacd989bib50","article-title":"Liegg: studying learned lie group generators","author":"Moskalev","year":"2022"},{"key":"mlstacd989bib51","first-page":"pp 8024","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"mlstacd989bib52","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"mlstacd989bib53","author":"Hladik","year":"yr1999"},{"key":"mlstacd989bib54","article-title":"Oracle-preserving latent flows","author":"Alexander Roman","year":"2023"},{"key":"mlstacd989bib55","first-page":"315","article-title":"Complex spinors and unified theories","volume":"790927","author":"Gell-Mann","year":"1979"},{"key":"mlstacd989bib56","doi-asserted-by":"crossref","DOI":"10.1016\/j.physletb.2023.138086","article-title":"Discovering sparse representations of lie groups with machine learning","author":"Forestano","year":"2023"},{"key":"mlstacd989bib57","article-title":"Deep learning symmetries","author":"Forestano","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T04:58:49Z","timestamp":1702529929000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd989"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":57,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,6,8]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acd989","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"assertion":[{"value":"Deep learning symmetries and their Lie groups, algebras, and subalgebras from first principles","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-02-13","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-05-26","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}