{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T11:57:04Z","timestamp":1781265424989,"version":"3.54.1"},"reference-count":34,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:00:00Z","timestamp":1652486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["21-72-00157"],"award-info":[{"award-number":["21-72-00157"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["0657-2020-0005"],"award-info":[{"award-number":["0657-2020-0005"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004569","name":"Ministry of Science and Higher Education","doi-asserted-by":"publisher","award":["21-72-00157"],"award-info":[{"award-number":["21-72-00157"]}],"id":[{"id":"10.13039\/501100004569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004569","name":"Ministry of Science and Higher Education","doi-asserted-by":"publisher","award":["0657-2020-0005"],"award-info":[{"award-number":["0657-2020-0005"]}],"id":[{"id":"10.13039\/501100004569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Spin glass is the simplest disordered system that preserves the full range of complex collective behavior of interacting frustrating elements. In the paper, we propose a novel approach for calculating the values of thermodynamic averages of the frustrated spin glass model using custom deep neural networks. The spin glass system was considered as a specific weighted graph whose spatial distribution of the edges values determines the fundamental characteristics of the system. Special neural network architectures that mimic the structure of spin lattices have been proposed, which has increased the speed of learning and the accuracy of the predictions compared to the basic solution of fully connected neural networks. At the same time, the use of trained neural networks can reduce simulation time by orders of magnitude compared to other classical methods. The validity of the results is confirmed by comparison with numerical simulation with the replica-exchange Monte Carlo method.<\/jats:p>","DOI":"10.3390\/e24050697","type":"journal-article","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T09:27:56Z","timestamp":1652520476000},"page":"697","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A New Look at the Spin Glass Problem from a Deep Learning Perspective"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4518-6588","authenticated-orcid":false,"given":"Petr","family":"Andriushchenko","sequence":"first","affiliation":[{"name":"National Center for Cognitive Research, ITMO University, bldg. A, Kronverksky Pr. 49, 197101 Saint Petersburg, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9815-1891","authenticated-orcid":false,"given":"Dmitrii","family":"Kapitan","sequence":"additional","affiliation":[{"name":"National Center for Cognitive Research, ITMO University, bldg. A, Kronverksky Pr. 49, 197101 Saint Petersburg, Russia"},{"name":"Department of Theoretical Physics and Smart Technologies, Far Eastern Federal University, Russky Island, 10 Ajax Bay, 690922 Vladivostok, Russia"},{"name":"Institute of Applied Mathematics, Far Eastern Branch, Russian Academy of Science, 7 Radio, 690041 Vladivostok, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5068-8910","authenticated-orcid":false,"given":"Vitalii","family":"Kapitan","sequence":"additional","affiliation":[{"name":"Department of Theoretical Physics and Smart Technologies, Far Eastern Federal University, Russky Island, 10 Ajax Bay, 690922 Vladivostok, Russia"},{"name":"Institute of Applied Mathematics, Far Eastern Branch, Russian Academy of Science, 7 Radio, 690041 Vladivostok, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1088\/0305-4608\/5\/5\/017","article-title":"Theory of spin glasses","volume":"5","author":"Edwards","year":"1975","journal-title":"J. Phys. Met. Phys."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4384","DOI":"10.1103\/PhysRevB.17.4384","article-title":"Infinite-ranged models of spin-glasses","volume":"17","author":"Kirkpatrick","year":"1978","journal-title":"Phys. Rev. B"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1103\/PhysRevB.41.2261","article-title":"Nonequilibrium entropy and entropy distributions","volume":"41","author":"Langer","year":"1990","journal-title":"Phys. Rev. B"},{"key":"ref_4","unstructured":"Zarinelli, E. (2012). Spin-Glass Models and Interdisciplinary Applications. [Ph.D. Thesis, \u00c9cole Doctorale Physique de la r\u00e9Gion Parisienne]."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02846491","article-title":"Spin glass, the travelling salesman problem, neural networks and all that","volume":"36","author":"Venkataraman","year":"1991","journal-title":"Pramana"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1103\/PhysRevLett.55.1530","article-title":"Storing infinite numbers of patterns in a spin-glass model of neural networks","volume":"55","author":"Amit","year":"1985","journal-title":"Phys. Rev. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"053308","DOI":"10.1103\/PhysRevE.98.053308","article-title":"Optimization of population annealing Monte Carlo for large-scale spin-glass simulations","volume":"98","author":"Barzegar","year":"2018","journal-title":"Phys. Rev. E"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.1103\/PhysRevLett.57.2607","article-title":"Replica Monte Carlo simulation of spin-glasses","volume":"57","author":"Swendsen","year":"1986","journal-title":"Phys. Rev. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1016\/j.jmmm.2018.12.058","article-title":"Influence of cutoff dipole interaction radius and dilution on phase transition in kagome artificial spin ice","volume":"476","author":"Andriushchenko","year":"2019","journal-title":"J. Magn. Magn. Mater."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"022138","DOI":"10.1103\/PhysRevE.99.022138","article-title":"Large peaks in the entropy of the diluted nearest-neighbor spin-ice model on the pyrochlore lattice in a [111] magnetic field","volume":"99","author":"Andriushchenko","year":"2019","journal-title":"Phys. Rev. E"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1016\/j.physleta.2019.01.037","article-title":"Comparison of diluted antiferromagnetic Ising models on frustrated lattices in a magnetic field","volume":"383","author":"Soldatov","year":"2019","journal-title":"Phys. Lett. A"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kovtanyuk, A., Nefedev, K., and Prokhorov, I. (2010). Advanced computing method for solving of the polarized-radiation transfer equation. Russia-Taiwan Symposium on Methods and Tools of Parallel Processing, Springer.","DOI":"10.1007\/978-3-642-14822-4_30"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1134\/S1063776117060152","article-title":"Multicanonical sampling of the space of states of H(2, n)-vector models","volume":"124","author":"Shevchenko","year":"2017","journal-title":"J. Exp. Theor. Phys."},{"key":"ref_14","first-page":"244","article-title":"Concentration phase transition in a two-dimensional ferromagnet. Solid State Phenomena","volume":"312","author":"Chepak","year":"2020","journal-title":"Trans. Tech. Publ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.20537\/2076-7633-2020-12-5-1051-1061","article-title":"Numerical simulation of two-dimensional magnetic skyrmion structures","volume":"12","author":"Perzhu","year":"2020","journal-title":"Comput. Res. Model."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Landau, D., and Binder, K. (2021). A Guide to Monte Carlo Simulations in Statistical Physics, Cambridge University Press.","DOI":"10.1017\/9781108780346"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"012199","DOI":"10.1088\/1742-6596\/741\/1\/012199","article-title":"Approaches to numerical solution of 2D Ising model","volume":"741","author":"Soldatov","year":"2016","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1134\/S0021364019220090","article-title":"On the numerical calculation of frustrations in the Ising model","volume":"110","author":"Makarov","year":"2019","journal-title":"JETP Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MM.2018.112130030","article-title":"A new golden age in computer architecture: Empowering the machine-learning revolution","volume":"38","author":"Dean","year":"2018","journal-title":"IEEE Micro"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"045002","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"174435","DOI":"10.1103\/PhysRevB.97.174435","article-title":"Parameter diagnostics of phases and phase transition learning by neural networks","volume":"97","author":"Suchsland","year":"2018","journal-title":"Phys. Rev. B"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1038\/nphys4035","article-title":"Machine learning phases of matter","volume":"13","author":"Carrasquilla","year":"2017","journal-title":"Nat. Phys."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1038\/s41598-020-58263-5","article-title":"Machine-learning studies on spin models","volume":"10","author":"Shiina","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"015041","DOI":"10.1063\/9.0000082","article-title":"Numerical simulation of magnetic skyrmions on flat lattices","volume":"11","author":"Kapitan","year":"2021","journal-title":"AIP Adv."},{"key":"ref_26","first-page":"500","article-title":"Calculation of the ground states of spin glasses using the Restricted Boltzmann Machine","volume":"115","author":"Korol","year":"2022","journal-title":"JETP Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"147","DOI":"10.21468\/SciPostPhys.10.6.147","article-title":"Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape","volume":"10","author":"Bukov","year":"2021","journal-title":"SciPost Phys."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control. Signals Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Newman, M.E., and Barkema, G.T. (1999). Monte Carlo Methods in Statistical Physics, Clarendon Press.","DOI":"10.1093\/oso\/9780198517962.001.0001"},{"key":"ref_30","unstructured":"Wolfram, S. (2002). A New Kind of Science, Wolfram Media."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Janocha, K., and Czarnecki, W.M. (2017). On loss functions for deep neural networks in classification. arXiv.","DOI":"10.4467\/20838476SI.16.004.6185"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"El-Amir, H., and Hamdy, M. (2020). Deep Learning Fundamentals. Deep Learning Pipeline, Springer.","DOI":"10.1007\/978-1-4842-5349-6"},{"key":"ref_33","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Padalko, M.A., Shevchenko, Y.A., Kapitan, V.Y., and Nefedev, K.V. (2022). Parallel Computing of Edwards-Anderson Model. Algorithms, 15.","DOI":"10.3390\/a15010013"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/5\/697\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:10:42Z","timestamp":1760137842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/5\/697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,14]]},"references-count":34,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["e24050697"],"URL":"https:\/\/doi.org\/10.3390\/e24050697","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,14]]}}}