{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:35:43Z","timestamp":1775687743565,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3457863","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T18:37:31Z","timestamp":1726079851000},"page":"136131-136147","source":"Crossref","is-referenced-by-count":1,"title":["A Generalist Reinforcement Learning Agent for Compressing Multiple Convolutional Networks Using Singular Value Decomposition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7931-4654","authenticated-orcid":false,"given":"Gabriel","family":"Gonzalez-Sahagun","sequence":"first","affiliation":[{"name":"School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Nuevo Leon, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6270-3164","authenticated-orcid":false,"given":"Santiago Enrique","family":"Conant-Pablos","sequence":"additional","affiliation":[{"name":"School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Nuevo Leon, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3408-2166","authenticated-orcid":false,"given":"Jos\u00e9","family":"Carlos Ortiz-Bayliss","sequence":"additional","affiliation":[{"name":"School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Nuevo Leon, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-7864","authenticated-orcid":false,"given":"Jorge M.","family":"Cruz-Duarte","sequence":"additional","affiliation":[{"name":"School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Nuevo Leon, Mexico"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2270","article-title":"Learning the number of neurons in deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Alvarez"},{"key":"ref2","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016","journal-title":"arXiv:1608.08710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03508-1"},{"key":"ref4","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03221-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2016.7460664"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-023-01274-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref9","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00907"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref14","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref15","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","author":"Ashok","year":"2017","journal-title":"arXiv:1709.06030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2020.2999956"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3188119"},{"key":"ref19","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-022-03793-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07161-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_15"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11058-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10566-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2811"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3385857"},{"key":"ref28","first-page":"25656","article-title":"Topology-aware network pruning using multi-stage graph embedding and reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref31","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref33","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref34","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref35","article-title":"Deep learning for classical Japanese literature","author":"Clanuwat","year":"2018","journal-title":"arXiv:1812.01718"},{"key":"ref36","volume-title":"MNIST Handwritten Digit Database","author":"LeCun","year":"2010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115053"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref40","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546129"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref43","first-page":"15625","article-title":"Sparse weight activation training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Raihan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10677015.pdf?arnumber=10677015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T18:26:22Z","timestamp":1727893582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10677015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3457863","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}