{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T16:05:48Z","timestamp":1774195548485,"version":"3.50.1"},"reference-count":62,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018694","name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018694","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.2022.3176809","type":"journal-article","created":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T19:39:56Z","timestamp":1654717196000},"page":"733-744","source":"Crossref","is-referenced-by-count":12,"title":["Dynamic Probabilistic Pruning: A General Framework for Hardware-Constrained Pruning at Different Granularities"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6038-0664","authenticated-orcid":false,"given":"Lizeth","family":"Gonzalez-Carabarin","sequence":"first","affiliation":[{"name":"Electrical Engineering Department, Eindhoven University of Technology, Eindhoven, AP, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2629-3898","authenticated-orcid":false,"given":"Iris A. M.","family":"Huijben","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Eindhoven University of Technology, Eindhoven, AP, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Veeling","sequence":"additional","affiliation":[{"name":"Bastian Veeling with the AMLab, Informatics Institute, University of Amsterdam, Amsterdam, XH, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6730-0193","authenticated-orcid":false,"given":"Alexandre","family":"Schmid","sequence":"additional","affiliation":[{"name":"School of Engineering, EPFL, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2845-0495","authenticated-orcid":false,"given":"Ruud J. G.","family":"van Sloun","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Eindhoven University of Technology, Eindhoven, AP, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003474"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003871"},{"key":"ref3","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng","year":"2019","journal-title":"arXiv:1710.09282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2018.8357072"},{"key":"ref5","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","article-title":"Binarynet: Training deep neural networks with weights and activations constrained to +1 or \u22121","author":"Courbariaux","year":"2016","journal-title":"arXiv:1602.02830"},{"key":"ref7","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Represent. Learn. Workshop","author":"Hinton"},{"key":"ref8","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":"ref9","first-page":"598","article-title":"Optimal brain damage","volume-title":"Advances in Neural Information Processing Systems","author":"LeCun","year":"1990"},{"key":"ref10","first-page":"177","article-title":"1811.01907ring biases for minimal network construction with back-propagation","volume-title":"Advances in Neural Information Processing Systems","author":"Hanson","year":"1989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2952864"},{"key":"ref12","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2554688.2554785"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.23"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/RECONFIG.2018.8641739"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2019.00033"},{"key":"ref20","article-title":"Deep probabilistic subsampling for task-adaptive compressed sensing","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Huijben"},{"key":"ref21","article-title":"Learning N:M fine-grained structured sparse neural networks from scratch","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref22","article-title":"Learning both weights and connections for efficient neural networks","author":"Han","year":"2015","journal-title":"arXiv:1506.02626"},{"key":"ref23","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref24","article-title":"Exploring sparsity in recurrent neural networks","author":"Narang","year":"2017","journal-title":"arXiv:1704.05119"},{"key":"ref25","article-title":"Deep rewiring: Training very sparse deep networks","author":"Bellec","year":"2017","journal-title":"arXiv:1711.05136"},{"key":"ref26","article-title":"Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization","author":"Mostafa","year":"2019","journal-title":"arXiv:1902.05967"},{"key":"ref27","article-title":"Sparse networks from scratch: Faster training without losing performance","author":"Dettmers","year":"2019","journal-title":"arXiv:1907.04840"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021698"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref31","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016","journal-title":"arXiv:1608.08710"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref35","article-title":"Network pruning via transformable architecture search","author":"Dong","year":"2019","journal-title":"arXiv:1905.09717"},{"key":"ref36","article-title":"Learning structured sparsity in deep neural networks","author":"Wen","year":"2016","journal-title":"arXiv:1608.03665"},{"key":"ref37","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref38","article-title":"Operation-aware soft channel pruning using differentiable masks","author":"Kang","year":"2020","journal-title":"arXiv:2007.03938"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6098"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"ref41","article-title":"PENNI: Pruned kernel sharing for efficient CNN inference","author":"Li","year":"2020","journal-title":"arXiv:2005.07133"},{"key":"ref42","volume-title":"A100 Tensor Core GPU Architecture","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/544"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2972520"},{"key":"ref45","article-title":"A unified framework of DNN weight pruning and weight clustering\/quantization using ADMM","author":"Ye","year":"2018","journal-title":"arXiv:1811.01907"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6138"},{"key":"ref48","article-title":"HAQ: Hardware-aware automated quantization","author":"Wang","year":"2018","journal-title":"arXiv:1811.08886"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref50","article-title":"Learning sparsity and quantization jointly and automatically for neural network compression via constrained optimization","author":"Yang","year":"2019","journal-title":"arXiv:1910.05897"},{"key":"ref51","first-page":"5584","article-title":"Focused quantization for sparse CNNs","volume-title":"Advances in Neural Information Processing Systems","author":"Zhao","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053331"},{"key":"ref53","article-title":"Statistical theory of extreme values and some practical applications","volume":"33","author":"Gumbel","year":"1954"},{"key":"ref54","article-title":"Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement","author":"Kool","year":"2019","journal-title":"arXiv:1903.06059"},{"key":"ref55","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Jang"},{"key":"ref56","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maddison"},{"key":"ref57","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"Courbariaux","year":"2015","journal-title":"arXiv:1511.00363"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref59","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv:1409.1556"},{"key":"ref60","article-title":"Dynamic sparse training: Find efficient sparse network from scratch with trainable masked layers","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref61","article-title":"A gradient flow framework for analyzing network pruning","author":"Lubana","year":"2020","journal-title":"arXiv:2009.11839"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09790881.pdf?arnumber=9790881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:09:49Z","timestamp":1705021789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9790881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3176809","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}