{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T07:08:39Z","timestamp":1778828919023,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Tampere University Graduate School"},{"DOI":"10.13039\/501100005637","name":"Tekniikan Edist\u00e4miss\u00e4\u00e4ti\u00f6","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005637","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["310489"],"award-info":[{"award-number":["310489"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["297893"],"award-info":[{"award-number":["297893"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010664","name":"European Union\u2019s Horizon 2020 Framework Program for Research and Innovation","doi-asserted-by":"publisher","award":["785907"],"award-info":[{"award-number":["785907"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010664","name":"European Union\u2019s Horizon 2020 Framework Program for Research and Innovation","doi-asserted-by":"publisher","award":["945539"],"award-info":[{"award-number":["945539"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tnnls.2022.3175757","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T19:33:25Z","timestamp":1653593605000},"page":"519-531","source":"Crossref","is-referenced-by-count":22,"title":["Accelerating Neural ODEs Using Model Order Reduction"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0396-3254","authenticated-orcid":false,"given":"Mikko","family":"Lehtim\u00e4ki","sequence":"first","affiliation":[{"name":"Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6497-4718","authenticated-orcid":false,"given":"Lassi","family":"Paunonen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marja-Leena","family":"Linne","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"1","key":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40304-017-0103-z","article-title":"A proposal on machine learning via dynamical systems","volume":"5","author":"Weinan","year":"2017","journal-title":"Commun. Math. Statist."},{"key":"ref3","first-page":"3276","article-title":"Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90"},{"key":"ref5","first-page":"6571","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref6","first-page":"5320","article-title":"Latent ordinary differential equations for irregularly-sampled time series","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rubanova"},{"key":"ref7","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proc. 2nd Int. Conf. Mach. Learn. Syst.","volume":"2","author":"Blalock"},{"key":"ref8","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref9","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref10","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2015.09.029"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-010-0229-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2014.00164"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.1143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073844"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fl.25.010193.002543"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/090766498"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2004.08.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/110822724"},{"key":"ref22","article-title":"Improving the speed of neural networks on CPUs","volume-title":"Proc. Deep Learn. Unsupervised Feature Learn. Workshop, NIPS","author":"Vanhoucke"},{"key":"ref23","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courbariaux"},{"key":"ref24","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9488"},{"key":"ref26","article-title":"Fast training of convolutional networks through FFTs","volume-title":"Proc. 2nd Int. Conf. Learn. Represent. (ICLR)","author":"Mathieu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2654822.2541967"},{"key":"ref28","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref29","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hassibi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-552"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.355"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref36","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014","journal-title":"arXiv:1412.6115"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24553-9_83"},{"key":"ref39","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Han"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref41","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Molchanov"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24425\/bpas.2018.125927"},{"key":"ref43","article-title":"Augmented neural ODEs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dupont"},{"key":"ref44","first-page":"4370","article-title":"Learning differential equations that are easy to solve","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kelly"},{"key":"ref45","first-page":"3154","article-title":"How to train your neural ODE: The world of Jacobian and kinetic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finlay"},{"key":"ref46","first-page":"5443","article-title":"Hey, that\u2019s not an ODE\u2019: Faster ODE adjoints via seminorms","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kidger"},{"key":"ref47","first-page":"21105","article-title":"Hypersolvers: Toward fast continuous-depth models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Poli"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"Stable neural flows","author":"Massaroli","year":"2020","journal-title":"arXiv:2003.08063"},{"key":"ref50","article-title":"AntisymmetricRNN: A dynamical system view on recurrent neural networks","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Chang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/910462"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/19M1307391"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4310\/SII.2016.v9.n4.a5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref55","article-title":"TorchDyn: A neural differential equations library","author":"Poli","year":"2020","journal-title":"arXiv:2009.09346"},{"key":"ref56","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref57","article-title":"Balanced truncation model order reduction for quadratic-bilinear control systems","author":"Benner","year":"2017","journal-title":"arXiv:1705.00160"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/15M1019271"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/130924408"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/140989169"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.apnum.2017.02.014"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09782503.pdf?arnumber=9782503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T04:12:45Z","timestamp":1723867965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9782503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":61,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3175757","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}