{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:03:38Z","timestamp":1781276618223,"version":"3.54.1"},"reference-count":13,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109018","type":"journal-article","created":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T22:24:21Z","timestamp":1777242261000},"page":"109018","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A quantifier-reversal approximation paradigm for recurrent neural networks"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3008-8106","authenticated-orcid":false,"given":"Clemens","family":"Hutter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6590-8050","authenticated-orcid":false,"given":"Valentin","family":"Abadie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3047-5149","authenticated-orcid":false,"given":"Helmut","family":"B\u00f6lcskei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.neunet.2026.109018_bib0001","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/18.256500","article-title":"Universal approximation bounds for superpositions of a sigmoidal function","volume":"39","author":"Barron","year":"1993","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"10.1016\/j.neunet.2026.109018_bib0002","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1023\/A:1022650905902","article-title":"Approximation and estimation bounds for artificial neural networks","volume":"14","author":"Barron","year":"1994","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109018_bib0003","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.camwa.2021.05.018","article-title":"Recurrent neural networks as optimal mesh refinement strategies","volume":"97","author":"Bohn","year":"2021","journal-title":"Computers & Mathematics with Applications"},{"issue":"4","key":"10.1016\/j.neunet.2026.109018_bib0004","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":"Mathematics of Control, Signals and Systems"},{"issue":"5","key":"10.1016\/j.neunet.2026.109018_bib0005","doi-asserted-by":"crossref","first-page":"2581","DOI":"10.1109\/TIT.2021.3062161","article-title":"Deep neural network approximation theory","volume":"67","author":"Elbr\u00e4chter","year":"2021","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2","key":"10.1016\/j.neunet.2026.109018_bib0006","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cognitive Science"},{"issue":"3","key":"10.1016\/j.neunet.2026.109018_bib0007","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","article-title":"On the approximate realization of continuous mappings by neural networks","volume":"2","author":"Funahashi","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109018_bib0008","series-title":"Deep learning","author":"Goodfellow","year":"2016"},{"issue":"5","key":"10.1016\/j.neunet.2026.109018_bib0009","doi-asserted-by":"crossref","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 Networks"},{"key":"10.1016\/j.neunet.2026.109018_bib0010","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2021.01.020","article-title":"The Kolmogorov\u2013Arnold representation theorem revisited","volume":"137","author":"Schmidt-Hieber","year":"2021","journal-title":"Neural Networks"},{"issue":"357","key":"10.1016\/j.neunet.2026.109018_bib0011","first-page":"1","article-title":"Optimal approximation rates for deep ReLU neural networks on Sobolev and Besov spaces","volume":"24","author":"Siegel","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109018_bib0012","series-title":"Proceedings of the 34th international conference on machine learning","first-page":"3387","article-title":"Neural networks and rational functions","author":"Telgarsky","year":"2017"},{"key":"10.1016\/j.neunet.2026.109018_bib0013","doi-asserted-by":"crossref","unstructured":"Yarotsky, D. (2017). Error bounds for approximations with deep ReLU networks. 94, 103\u2013114. 10.1016\/j.neunet.2017.07.002.","DOI":"10.1016\/j.neunet.2017.07.002"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004788?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004788?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T14:51:38Z","timestamp":1781275898000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":13,"alternative-id":["S0893608026004788"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109018","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A quantifier-reversal approximation paradigm for recurrent neural networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109018","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109018"}}