{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:50:43Z","timestamp":1740181843344,"version":"3.37.3"},"reference-count":42,"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"}],"funder":[{"name":"IML4E Project of ITEA4"},{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Comput. Soc."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/ojcs.2024.3467182","type":"journal-article","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T19:32:18Z","timestamp":1727292738000},"page":"542-552","source":"Crossref","is-referenced-by-count":0,"title":["Removing Neurons From Deep Neural Networks Trained With Tabular Data"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6578-6284","authenticated-orcid":false,"given":"Antti","family":"Klemetti","sequence":"first","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2410-0722","authenticated-orcid":false,"given":"Mikko","family":"Raatikainen","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9673-9760","authenticated-orcid":false,"given":"Juhani","family":"Kivim\u00e4ki","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0953-9825","authenticated-orcid":false,"given":"Lalli","family":"Myllyaho","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-1927","authenticated-orcid":false,"given":"Jukka K.","family":"Nurminen","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $< $0.5 MB model size","year":"2016","author":"Iandola","key":"ref4"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref5"},{"article-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref6"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"article-title":"LLaMA: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref8"},{"issue":"8","key":"ref9","first-page":"6679","article-title":"TabNet: Attentive interpretable tabular learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Arik","year":"2021"},{"key":"ref10","first-page":"1","article-title":"Ten lessons from three generations shaped googles TPUv4i : Industrial product","volume-title":"2021 ACM\/IEEE 48th Annu. Int. Symp. Comput. Architecture","author":"Jouppi","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3275431"},{"key":"ref16","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Ba","year":"2014"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref17"},{"key":"ref18","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.021"},{"year":"2022","key":"ref21","article-title":"Winning solutions of kaggle competitions"},{"key":"ref22","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"ref24","article-title":"Unified embedding: Battle-tested feature representations for web-scale ML systems","volume":"36","author":"Coleman","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"LeCun","year":"1989"},{"key":"ref26","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"5","author":"Hassibi","year":"1992"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","year":"2016","author":"Han","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref29","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Wen","year":"2016"},{"article-title":"Pruning filters for efficient ConvNets","year":"2017","author":"Li","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102336"},{"year":"2024","key":"ref33","article-title":"Pruning Tutorial  PyTorch Tutorials 2.0.1 cu117 documentation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2021.100907"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2876857"},{"article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","year":"2019","author":"Frankle","key":"ref36"},{"article-title":"Rethinking the value of network pruning","year":"2019","author":"Liu","key":"ref37"},{"year":"2020","key":"ref38","article-title":"Mechanisms of action (MoA) prediction"},{"year":"2021","key":"ref39","article-title":"Google brain - ventilator pressure prediction"},{"year":"2019","key":"ref40","article-title":"Predicting molecular properties"},{"article-title":"Torch-trim-pruned","year":"2023","author":"Klemetti","key":"ref41"},{"year":"2024","key":"ref42","article-title":"Puhti.csc"}],"container-title":["IEEE Open Journal of the Computer Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782664\/10375894\/10693557.pdf?arnumber=10693557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:38:26Z","timestamp":1728560306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10693557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ojcs.2024.3467182","relation":{},"ISSN":["2644-1268"],"issn-type":[{"type":"electronic","value":"2644-1268"}],"subject":[],"published":{"date-parts":[[2024]]}}}