From Spin Glasses to Learning of Neural Networks

— The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extrac...

Full description

Saved in:
Bibliographic Details
Published in:Physics of particles and nuclei 2022-08, Vol.53 (4), p.834-847
Main Authors: Perepelkin, E. E., Sadovnikov, B. I., Inozemtseva, N. G., Rudamenko, R. A., Tarelkin, A. A., Sysoev, P. N., Polyakova, R. V., Sadovnikova, M. B.
Format: Article
Language:English
Subjects:
Particle and Nuclear Physics
Physics
Physics and Astronomy
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c170t-a99c920c1e143180601a17bd3404efb0b128f6add07aab237798e2b1896c35753
container_end_page 847
container_issue 4
container_start_page 834
container_title Physics of particles and nuclei
container_volume 53
creator Perepelkin, E. E.
Sadovnikov, B. I.
Inozemtseva, N. G.
Rudamenko, R. A.
Tarelkin, A. A.
Sysoev, P. N.
Polyakova, R. V.
Sadovnikova, M. B.
description — The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extract the learning algorithm hyperparameter, temperature, has been described and used. Critical phenomena in the RBM—entropy crisis, and difference between the temperatures of the learning sample creation and processing—are studied.
doi_str_mv 10.1134/S1063779622040128
format article
fullrecord <record><control><sourceid>crossref_sprin</sourceid><recordid>TN_cdi_crossref_primary_10_1134_S1063779622040128</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1134_S1063779622040128</sourcerecordid><originalsourceid>FETCH-LOGICAL-c170t-a99c920c1e143180601a17bd3404efb0b128f6add07aab237798e2b1896c35753</originalsourceid><addsrcrecordid>eNp9j1FLwzAUhYMoOKc_wLf8geq9SdMkjzLcHBR92PZc0jYZnV0zkg7x35sy3wSfzoVzvss5hDwiPCHy_HmDUHApdcEY5IBMXZEZCo6ZEkJfpzvZ2eTfkrsYDwCIKNSMwDL4I92cuoGuehOjjXT0tLQmDN2wp97Rd3sOpk8yfvnwGe_JjTN9tA-_Oie75et28ZaVH6v14qXMGpQwZkbrRjNo0GLOUUEBaFDWLc8ht66GOlV0hWlbkMbUbKquLKtR6aLhQgo-J3j52wQfY7CuOoXuaMJ3hVBNk6s_kxPDLkxM2WFvQ3Xw5zCkmv9AP3FOVjI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>From Spin Glasses to Learning of Neural Networks</title><source>Springer Nature:Jisc Collections:Springer Nature Read and Publish 2023-2025: Springer Reading List</source><creator>Perepelkin, E. E. ; Sadovnikov, B. I. ; Inozemtseva, N. G. ; Rudamenko, R. A. ; Tarelkin, A. A. ; Sysoev, P. N. ; Polyakova, R. V. ; Sadovnikova, M. B.</creator><creatorcontrib>Perepelkin, E. E. ; Sadovnikov, B. I. ; Inozemtseva, N. G. ; Rudamenko, R. A. ; Tarelkin, A. A. ; Sysoev, P. N. ; Polyakova, R. V. ; Sadovnikova, M. B.</creatorcontrib><description>— The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extract the learning algorithm hyperparameter, temperature, has been described and used. Critical phenomena in the RBM—entropy crisis, and difference between the temperatures of the learning sample creation and processing—are studied.</description><identifier>ISSN: 1063-7796</identifier><identifier>EISSN: 1531-8559</identifier><identifier>DOI: 10.1134/S1063779622040128</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Particle and Nuclear Physics ; Physics ; Physics and Astronomy</subject><ispartof>Physics of particles and nuclei, 2022-08, Vol.53 (4), p.834-847</ispartof><rights>Pleiades Publishing, Ltd. 2022. ISSN 1063-7796, Physics of Particles and Nuclei, 2022, Vol. 53, No. 4, pp. 834–847. © Pleiades Publishing, Ltd., 2022. Russian Text © The Author(s), 2022, published in Fizika Elementarnykh Chastits i Atomnogo Yadra, 2022, Vol. 53, No. 4.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c170t-a99c920c1e143180601a17bd3404efb0b128f6add07aab237798e2b1896c35753</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Perepelkin, E. E.</creatorcontrib><creatorcontrib>Sadovnikov, B. I.</creatorcontrib><creatorcontrib>Inozemtseva, N. G.</creatorcontrib><creatorcontrib>Rudamenko, R. A.</creatorcontrib><creatorcontrib>Tarelkin, A. A.</creatorcontrib><creatorcontrib>Sysoev, P. N.</creatorcontrib><creatorcontrib>Polyakova, R. V.</creatorcontrib><creatorcontrib>Sadovnikova, M. B.</creatorcontrib><title>From Spin Glasses to Learning of Neural Networks</title><title>Physics of particles and nuclei</title><addtitle>Phys. Part. Nuclei</addtitle><description>— The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extract the learning algorithm hyperparameter, temperature, has been described and used. Critical phenomena in the RBM—entropy crisis, and difference between the temperatures of the learning sample creation and processing—are studied.</description><subject>Particle and Nuclear Physics</subject><subject>Physics</subject><subject>Physics and Astronomy</subject><issn>1063-7796</issn><issn>1531-8559</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp9j1FLwzAUhYMoOKc_wLf8geq9SdMkjzLcHBR92PZc0jYZnV0zkg7x35sy3wSfzoVzvss5hDwiPCHy_HmDUHApdcEY5IBMXZEZCo6ZEkJfpzvZ2eTfkrsYDwCIKNSMwDL4I92cuoGuehOjjXT0tLQmDN2wp97Rd3sOpk8yfvnwGe_JjTN9tA-_Oie75et28ZaVH6v14qXMGpQwZkbrRjNo0GLOUUEBaFDWLc8ht66GOlV0hWlbkMbUbKquLKtR6aLhQgo-J3j52wQfY7CuOoXuaMJ3hVBNk6s_kxPDLkxM2WFvQ3Xw5zCkmv9AP3FOVjI</recordid><startdate>20220801</startdate><enddate>20220801</enddate><creator>Perepelkin, E. E.</creator><creator>Sadovnikov, B. I.</creator><creator>Inozemtseva, N. G.</creator><creator>Rudamenko, R. A.</creator><creator>Tarelkin, A. A.</creator><creator>Sysoev, P. N.</creator><creator>Polyakova, R. V.</creator><creator>Sadovnikova, M. B.</creator><general>Pleiades Publishing</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20220801</creationdate><title>From Spin Glasses to Learning of Neural Networks</title><author>Perepelkin, E. E. ; Sadovnikov, B. I. ; Inozemtseva, N. G. ; Rudamenko, R. A. ; Tarelkin, A. A. ; Sysoev, P. N. ; Polyakova, R. V. ; Sadovnikova, M. B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c170t-a99c920c1e143180601a17bd3404efb0b128f6add07aab237798e2b1896c35753</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Particle and Nuclear Physics</topic><topic>Physics</topic><topic>Physics and Astronomy</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Perepelkin, E. E.</creatorcontrib><creatorcontrib>Sadovnikov, B. I.</creatorcontrib><creatorcontrib>Inozemtseva, N. G.</creatorcontrib><creatorcontrib>Rudamenko, R. A.</creatorcontrib><creatorcontrib>Tarelkin, A. A.</creatorcontrib><creatorcontrib>Sysoev, P. N.</creatorcontrib><creatorcontrib>Polyakova, R. V.</creatorcontrib><creatorcontrib>Sadovnikova, M. B.</creatorcontrib><collection>CrossRef</collection><jtitle>Physics of particles and nuclei</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Perepelkin, E. E.</au><au>Sadovnikov, B. I.</au><au>Inozemtseva, N. G.</au><au>Rudamenko, R. A.</au><au>Tarelkin, A. A.</au><au>Sysoev, P. N.</au><au>Polyakova, R. V.</au><au>Sadovnikova, M. B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>From Spin Glasses to Learning of Neural Networks</atitle><jtitle>Physics of particles and nuclei</jtitle><stitle>Phys. Part. Nuclei</stitle><date>2022-08-01</date><risdate>2022</risdate><volume>53</volume><issue>4</issue><spage>834</spage><epage>847</epage><pages>834-847</pages><issn>1063-7796</issn><eissn>1531-8559</eissn><abstract>— The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extract the learning algorithm hyperparameter, temperature, has been described and used. Critical phenomena in the RBM—entropy crisis, and difference between the temperatures of the learning sample creation and processing—are studied.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.1134/S1063779622040128</doi><tpages>14</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1063-7796
ispartof Physics of particles and nuclei, 2022-08, Vol.53 (4), p.834-847
issn 1063-7796
1531-8559
language eng
recordid cdi_crossref_primary_10_1134_S1063779622040128
source Springer Nature:Jisc Collections:Springer Nature Read and Publish 2023-2025: Springer Reading List
subjects Particle and Nuclear Physics
Physics
Physics and Astronomy
title From Spin Glasses to Learning of Neural Networks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T21%3A41%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=From%20Spin%20Glasses%20to%20Learning%20of%20Neural%20Networks&rft.jtitle=Physics%20of%20particles%20and%20nuclei&rft.au=Perepelkin,%20E.%20E.&rft.date=2022-08-01&rft.volume=53&rft.issue=4&rft.spage=834&rft.epage=847&rft.pages=834-847&rft.issn=1063-7796&rft.eissn=1531-8559&rft_id=info:doi/10.1134/S1063779622040128&rft_dat=%3Ccrossref_sprin%3E10_1134_S1063779622040128%3C/crossref_sprin%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c170t-a99c920c1e143180601a17bd3404efb0b128f6add07aab237798e2b1896c35753%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true