{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T22:47:03Z","timestamp":1776466023348,"version":"3.51.2"},"reference-count":41,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000166","name":"Division of Physics","doi-asserted-by":"crossref","award":["PHY-2019786"],"award-info":[{"award-number":["PHY-2019786"]}],"id":[{"id":"10.13039\/100000166","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":[[2023,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Following the earlier formalism of the categorical representation learning, we discuss the construction of the \u2018RG-flow-based categorifier\u2019. Borrowing ideas from the theory of renormalization group (RG) flows in quantum field theory, holographic duality, and hyperbolic geometry and combining them with neural ordinary differential equation techniques, we construct a new algorithmic natural language processing architecture, called the RG-flow categorifier or for short the RG categorifier, which is capable of data classification and generation in all layers. We apply our algorithmic platform to biomedical data sets and show its performance in the field of sequence-to-function mapping. In particular, we apply the RG categorifier to particular genomic sequences of flu viruses and show how our technology is capable of extracting the information from given genomic sequences, finding their hidden symmetries and dominant features, classifying them, and using the trained data to make a stochastic prediction of new plausible generated sequences associated with a new set of viruses which could avoid the human immune system.<\/jats:p>","DOI":"10.1088\/2632-2153\/acb488","type":"journal-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:40:07Z","timestamp":1674081607000},"page":"015012","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Categorical representation learning and RG flow operators for algorithmic classifiers"],"prefix":"10.1088","volume":"4","author":[{"given":"Artan","family":"Sheshmani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4080-5340","authenticated-orcid":true,"given":"Yi-Zhuang","family":"You","sequence":"additional","affiliation":[]},{"given":"Wenbo","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Ahmadreza","family":"Azizi","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,2,2]]},"reference":[{"key":"mlstacb488bib1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac2c5d","article-title":"Categorical representation learning: morphism is all you need","volume":"3","author":"Sheshmani","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstacb488bib2","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/0550-3213(84)90287-6","article-title":"Renormalization and effective Lagrangians","volume":"231","author":"Polchinski","year":"1984","journal-title":"Nucl. Phys. B"},{"key":"mlstacb488bib3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.4310\/jdg\/1214436922","article-title":"Three-manifolds with positive Ricci curvature","volume":"17","author":"Hamilton","year":"1982","journal-title":"J. Differ. Geom."},{"key":"mlstacb488bib4","doi-asserted-by":"publisher","first-page":"695","DOI":"10.4310\/CAG.1999.v7.n4.a2","article-title":"Non-singular solutions of the Ricci flow on three-manifolds","volume":"7","author":"Hamilton","year":"1999","journal-title":"Commun. Anal. Geom."},{"key":"mlstacb488bib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4310\/jdg\/1214454093","article-title":"Eternal solutions to the Ricci flow","volume":"38","author":"Hamilton","year":"1993","journal-title":"J. Differ. Geom."},{"key":"mlstacb488bib6","doi-asserted-by":"publisher","first-page":"69","DOI":"10.4310\/jdg\/1214439902","article-title":"The heat equation shrinking convex plane curves","volume":"23","author":"Gage","year":"1986","journal-title":"J. Differ. Geom."},{"key":"mlstacb488bib7","first-page":"pp 7","article-title":"The formation of singularities in the Ricci flow","author":"Hamilton","year":"1995"},{"key":"mlstacb488bib8","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1103\/PhysRevLett.45.1057","article-title":"Nonlinear models in 2 + \u03f5 dimensions","volume":"45","author":"Freidan","year":"1980","journal-title":"Phys.Rev.Lett."},{"key":"mlstacb488bib9","first-page":"565","article-title":"Irreversibility of the flux of the renormalization group in a 2D field theory","volume":"43","author":"Zomolodchikov","year":"1986","journal-title":"Pisma Zh. Eksp. Teor. Fiz."},{"key":"mlstacb488bib10","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/0370-2693(86)90465-X","article-title":"Conformal anomaly in a two-dimensional sigma model on a curved background and strings","volume":"178","author":"Tseytlin","year":"1986","journal-title":"Phys. Lett. B"},{"key":"mlstacb488bib11","article-title":"Ricci flow with surgery on three-manifolds","author":"Perelman","year":"2003"},{"key":"mlstacb488bib12","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00032-010-0110-y","article-title":"Renormalization group and the Ricci flow","volume":"78","author":"Carfora","year":"2010","journal-title":"Milan J. Math."},{"key":"mlstacb488bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.260601","article-title":"Neural network renormalization group","volume":"121","author":"Li","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstacb488bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.023369","article-title":"Machine learning holographic mapping by neural network renormalization group","volume":"2","author":"Hu","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstacb488bib15","article-title":"RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior","author":"Hu","year":"2020"},{"key":"mlstacb488bib16","article-title":"Neural ordinary differential equations","author":"Chen","year":"2018"},{"key":"mlstacb488bib17","article-title":"Deep learning and the renormalization group","author":"B\u00e9ny","year":"2013"},{"key":"mlstacb488bib18","article-title":"An exact mapping between the variational renormalization group and deep learning","author":"Mehta","year":"2014"},{"key":"mlstacb488bib19","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/17\/8\/083005","article-title":"The renormalization group via statistical inference","volume":"17","author":"B\u00e9ny","year":"2015","journal-title":"New J. Phys."},{"key":"mlstacb488bib20","article-title":"Criticality & deep learning I: generally weighted nets","author":"Oprisa","year":"2017"},{"key":"mlstacb488bib21","article-title":"Criticality & deep learning II: momentum renormalisation group","author":"Oprisa","year":"2017"},{"key":"mlstacb488bib22","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1007\/s10955-017-1836-5","article-title":"Why does deep and cheap learning work so well?","volume":"168","author":"Lin","year":"2017","journal-title":"J. Stat. Phys."},{"key":"mlstacb488bib23","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1038\/s41567-018-0081-4","article-title":"Mutual information, neural networks and the renormalization group","volume":"14","author":"Koch-Janusz","year":"2018","journal-title":"Nat. Phys."},{"key":"mlstacb488bib24","article-title":"Optimal renormalization group transformation from information theory","author":"Lenggenhager","year":"2018"},{"key":"mlstacb488bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.260601","article-title":"Neural network renormalization group","volume":"121","author":"Li","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstacb488bib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.023369","article-title":"Machine learning holographic mapping by neural network renormalization group","volume":"2","author":"Hu","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstacb488bib27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.023230","article-title":"Neural Monte Carlo renormalization group","volume":"3","author":"Chung","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstacb488bib28","author":"Cotler","year":"2022"},{"key":"mlstacb488bib29","article-title":"Exact holographic mapping and emergent space-time geometry","author":"Qi","year":"2013"},{"key":"mlstacb488bib30","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"mlstacb488bib31","article-title":"Theoretical limitations of self-attention in neural sequence models","author":"Hahn","year":"2019"},{"key":"mlstacb488bib32","article-title":"Constraints on beta functions in field theories","author":"Ma","year":"2020"},{"key":"mlstacb488bib33","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1186\/s12864-018-5370-x","article-title":"Gene2vec: distributed representation of genes based on co-expression","volume":"20","author":"Du","year":"2019","journal-title":"BMC Genomics"},{"key":"mlstacb488bib34","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1038\/s41598-020-80670-x","article-title":"A deep learning framework combined with word embedding to identify DNA replication origins","volume":"11","author":"Wu","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstacb488bib35","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1126\/science.abd7331","article-title":"Learning the language of viral evolution and escape","volume":"371","author":"Hie","year":"2021","journal-title":"Science"},{"key":"mlstacb488bib36","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"mlstacb488bib37","article-title":"How to train your neural ODE: the world of Jacobian and kinetic regularization","author":"Finlay","year":"2020"},{"key":"mlstacb488bib38","article-title":"Ffjord: free-form continuous dynamics for scalable reversible generative models","author":"Grathwohl","year":"2018"},{"key":"mlstacb488bib39","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacb488bib40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-03665-3","article-title":"How single mutations affect viral escape from broad and narrow antibodies to H1 influenza hemagglutinin","volume":"9","author":"Doud","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstacb488bib41","author":"Costello","year":"2011"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T13:56:46Z","timestamp":1699538206000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,2]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,2,2]]},"published-print":{"date-parts":[[2023,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acb488","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,2]]},"assertion":[{"value":"Categorical representation learning and RG flow operators for algorithmic classifiers","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":"2022-09-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-02-02","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}