{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:22:05Z","timestamp":1778613725760,"version":"3.51.4"},"reference-count":86,"publisher":"World Scientific Pub Co Pte Ltd","issue":"13","funder":[{"name":"the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund","award":["K146721"],"award-info":[{"award-number":["K146721"]}]},{"name":"the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund","award":["TKP2021-NVA-29"],"award-info":[{"award-number":["TKP2021-NVA-29"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:p>In this paper, we present a hybrid learning framework that integrates two model-driven AI paradigms: Deep unfolding and Variable Projections (VPs). The core idea is to unfold the iterations of VP solvers for separable nonlinear least squares (SNLLS) problems into trainable neural network layers. As a consequence, the network is capable of learning optimal nonlinear VP parameters during inference, which is a form of model-based meta-learning. Furthermore, the architecture incorporates prior knowledge of the underlying SNLLS problem, such as basis function expansions and signal structure, which enhance interpretability, reduce model size, and lower data requirements. As a case study, we adapt the proposed deep unfolded VPNet to learn ECG representations for the classification of five arrhythmias. Experimental results on the MIT-BIH Arrhythmia Database show that VPNet achieves performance comparable to state-of-the-art ECG classifiers, attaining \u00a095% accuracy while maintaining a compact architecture. Its low computational complexity enables efficient training and inference, making it highly suitable for real-time, power-efficient edge computing applications. This is further validated through embedded implementation on STM32 microcontrollers.<\/jats:p>","DOI":"10.1142\/s0129065725500534","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:22:23Z","timestamp":1756308143000},"source":"Crossref","is-referenced-by-count":1,"title":["Deep Unfolded Variable Projection Networks"],"prefix":"10.1142","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7818-5760","authenticated-orcid":false,"given":"Gerg\u0151","family":"Bogn\u00e1r","sequence":"first","affiliation":[{"name":"Department of Numerical Analysis, ELTE Eotvos Lorand University, P\u00e1zm\u00e1ny P\u00e9ter stny 1\/C, Budapest 1117, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8723-9251","authenticated-orcid":false,"given":"Manuel","family":"Feindert","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing, Johannes Kepler University Linz, Altenberger Street 69, Linz 4040, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5766-5332","authenticated-orcid":false,"given":"Christian","family":"Huber","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing, Johannes Kepler University Linz, Altenberger Street 69, Linz 4040, Austria"},{"name":"Silicon Austria Labs GmbH, Altenberger Street 69, Linz 4040, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4014-9681","authenticated-orcid":false,"given":"Michael","family":"Lunglmayr","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing, Johannes Kepler University Linz, Altenberger Street 69, Linz 4040, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3164-7232","authenticated-orcid":false,"given":"Mario","family":"Huemer","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing, Johannes Kepler University Linz, Altenberger Street 69, Linz 4040, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0772-9721","authenticated-orcid":false,"given":"P\u00e9ter","family":"Kov\u00e1cs","sequence":"additional","affiliation":[{"name":"Department of Numerical Analysis, ELTE Eotvos Lorand University, P\u00e1zm\u00e1ny P\u00e9ter stny 1\/C, Budapest 1117, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"S0129065725500534BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/OJEMB.2024.3379733"},{"key":"S0129065725500534BIB002","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztab090"},{"key":"S0129065725500534BIB003","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjcc.2021.11.017"},{"key":"S0129065725500534BIB004","unstructured":"A. Holzinger, C. Biemann, C. S. Pattichis and D. B. Kell, What do we need to build explainable AI systems for the medical domain? arXiv:1712.09923."},{"key":"S0129065725500534BIB005","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"issue":"1","key":"S0129065725500534BIB006","first-page":"614","volume":"35","author":"von Rueden L.","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"S0129065725500534BIB007","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"S0129065725500534BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3247480"},{"key":"S0129065725500534BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3338619"},{"key":"S0129065725500534BIB010","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04146-4"},{"key":"S0129065725500534BIB011","unstructured":"J. R. Hershey, J. L. Roux and F. Weninger, Deep unfolding: Model-based inspiration of novel deep architectures, arXiv:1409.2574."},{"key":"S0129065725500534BIB012","first-page":"399","volume-title":"Proc. 27th Int. Conf. Machine Learning, ICML\u2019 10","author":"Gregor K.","year":"2010"},{"key":"S0129065725500534BIB013","series-title":"Proceedings of Machine Learning Research","first-page":"6828","volume-title":"Proc. 36th Int. Conf. Machine Learning","volume":"97","author":"Wu S.","year":"2019"},{"key":"S0129065725500534BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3054167"},{"key":"S0129065725500534BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918878"},{"key":"S0129065725500534BIB016","series-title":"Proceedings of Machine Learning Research","first-page":"9493","volume-title":"Proc. 37th Int. Conf. Machine Learning","volume":"119","author":"Tolooshams B.","year":"2020"},{"key":"S0129065725500534BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2899805"},{"key":"S0129065725500534BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2976585"},{"key":"S0129065725500534BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3325367"},{"key":"S0129065725500534BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2020.2964202"},{"key":"S0129065725500534BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2941271"},{"key":"S0129065725500534BIB022","doi-asserted-by":"publisher","DOI":"10.1137\/0710036"},{"key":"S0129065725500534BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.629"},{"key":"S0129065725500534BIB024","doi-asserted-by":"publisher","DOI":"10.1137\/20M1359511"},{"key":"S0129065725500534BIB025","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/19\/2\/201"},{"key":"S0129065725500534BIB026","doi-asserted-by":"publisher","DOI":"10.4236\/ajcm.2019.94020"},{"key":"S0129065725500534BIB027","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721500544"},{"key":"S0129065725500534BIB028","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-012-9492-9"},{"key":"S0129065725500534BIB029","unstructured":"STMicroelectronics, STM32H723ZG datasheet (2023), Accessed 25 March 2025."},{"key":"S0129065725500534BIB030","unstructured":"STMicroelectronics, STM32F446RE Datasheet (2021), Accessed 25 March 2025."},{"key":"S0129065725500534BIB031","unstructured":"Association for the Advancement of Medical Instrumentation (AAMI), Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms, American National Standards Institute (ANSI) ANSI\/AAMI\/ISO EC57 (1998-(R)2008), (2012)."},{"key":"S0129065725500534BIB032","first-page":"52","volume-title":"Exponential Data Fitting and its Applications","author":"Paluszny M.","year":"2010"},{"key":"S0129065725500534BIB033","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1379"},{"key":"S0129065725500534BIB034","first-page":"1080","volume-title":"Proc. 44th IEEE Int. Conf. Acoustics Speech Signal Processing (ICASSP)","author":"Kov\u00e1cs P.","year":"2019"},{"key":"S0129065725500534BIB035","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3058781"},{"key":"S0129065725500534BIB036","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102034"},{"key":"S0129065725500534BIB037","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2961234"},{"key":"S0129065725500534BIB038","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3376315"},{"key":"S0129065725500534BIB039","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052907"},{"key":"S0129065725500534BIB040","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108871"},{"key":"S0129065725500534BIB041","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3155871"},{"key":"S0129065725500534BIB042","doi-asserted-by":"publisher","DOI":"10.1007\/BF01932995"},{"key":"S0129065725500534BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2267893"},{"key":"S0129065725500534BIB044","first-page":"1","volume-title":"Proc. Workshop Biosignals","author":"Kov\u00e1cs P.","year":"2024"},{"key":"S0129065725500534BIB045","doi-asserted-by":"publisher","DOI":"10.22489\/CinC.2022.049"},{"key":"S0129065725500534BIB046","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500047"},{"key":"S0129065725500534BIB047","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3194900"},{"key":"S0129065725500534BIB048","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3382931"},{"key":"S0129065725500534BIB049","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3475271"},{"key":"S0129065725500534BIB050","doi-asserted-by":"publisher","DOI":"10.22489\/CinC.2024.130"},{"key":"S0129065725500534BIB051","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC58623.2025.11253764"},{"key":"S0129065725500534BIB052","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"S0129065725500534BIB053","unstructured":"Open Neural Network Exchange (ONNX), https:\/\/onnx.ai\/, Accessed 25 March 2025."},{"key":"S0129065725500534BIB054","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2011.02.002"},{"key":"S0129065725500534BIB055","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2014.04.001"},{"key":"S0129065725500534BIB056","doi-asserted-by":"publisher","DOI":"10.1109\/51.932724"},{"key":"S0129065725500534BIB057","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"S0129065725500534BIB058","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2004.827359"},{"key":"S0129065725500534BIB059","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2015.12.008"},{"key":"S0129065725500534BIB060","first-page":"1212","volume-title":"2005 IEEE Engineering Medicine and Biology 27th Annual Conf.","author":"Zhang D.","year":"2005"},{"key":"S0129065725500534BIB061","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2213253"},{"key":"S0129065725500534BIB062","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45096-0_44"},{"key":"S0129065725500534BIB063","volume-title":"Orthogonal Polynomials","author":"Szeg\u0151 G.","year":"1967","edition":"3"},{"key":"S0129065725500534BIB064","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.1981.324666"},{"key":"S0129065725500534BIB065","doi-asserted-by":"publisher","DOI":"10.1007\/BF02637023"},{"key":"S0129065725500534BIB066","doi-asserted-by":"publisher","DOI":"10.1109\/10.846677"},{"key":"S0129065725500534BIB067","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2004.01.003"},{"key":"S0129065725500534BIB068","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2173336"},{"key":"S0129065725500534BIB069","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106086"},{"key":"S0129065725500534BIB070","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2068048"},{"key":"S0129065725500534BIB071","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/712474"},{"key":"S0129065725500534BIB072","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-019-00776-9"},{"key":"S0129065725500534BIB073","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102091"},{"key":"S0129065725500534BIB074","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106582"},{"key":"S0129065725500534BIB075","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.09.001"},{"issue":"1","key":"S0129065725500534BIB076","first-page":"9946596","volume":"2021","author":"Zhang J.","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"S0129065725500534BIB077","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare8040437"},{"issue":"8","key":"S0129065725500534BIB078","first-page":"1","volume":"13","author":"Qiao X.","year":"2023","journal-title":"Appl. Sci."},{"key":"S0129065725500534BIB079","unstructured":"D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980."},{"key":"S0129065725500534BIB080","doi-asserted-by":"publisher","DOI":"10.14232\/actacyb.312363"},{"key":"S0129065725500534BIB081","doi-asserted-by":"publisher","DOI":"10.3390\/s25092800"},{"key":"S0129065725500534BIB082","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3384349"},{"key":"S0129065725500534BIB083","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190448"},{"issue":"107","key":"S0129065725500534BIB084","first-page":"1","volume":"48","author":"Rafiei M. H.","year":"2024","journal-title":"J. Med. Syst."},{"key":"S0129065725500534BIB085","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04359-7"},{"key":"S0129065725500534BIB086","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2682102"}],"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065725500534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T07:17:13Z","timestamp":1766042233000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0129065725500534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":86,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,12,30]]}},"alternative-id":["10.1142\/S0129065725500534"],"URL":"https:\/\/doi.org\/10.1142\/s0129065725500534","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"value":"0129-0657","type":"print"},{"value":"1793-6462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"article-number":"2550053"}}