{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:55:33Z","timestamp":1774540533042,"version":"3.50.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Singapore Government\u2019s Research, Innovation and Enterprise 2020 Plan","award":["A1687b0033"],"award-info":[{"award-number":["A1687b0033"]}]},{"name":"Singapore Government\u2019s Research, Innovation and Enterprise 2020 Plan","award":["A1892b0026"],"award-info":[{"award-number":["A1892b0026"]}]},{"name":"Singapore Government\u2019s Research, Innovation and Enterprise 2020 Plan","award":["A18A1b0045"],"award-info":[{"award-number":["A18A1b0045"]}]},{"name":"SERC Central Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnnls.2022.3190451","type":"journal-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T19:37:58Z","timestamp":1661283478000},"page":"2575-2587","source":"Crossref","is-referenced-by-count":12,"title":["RCT: Resource Constrained Training for Edge AI"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8765-1783","authenticated-orcid":false,"given":"Tian","family":"Huang","sequence":"first","affiliation":[{"name":"Agency for Science Technology and Research (A*STAR), Institute of High Performance Computing, Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3415-3676","authenticated-orcid":false,"given":"Tao","family":"Luo","sequence":"additional","affiliation":[{"name":"Agency for Science Technology and Research (A*STAR), Institute of High Performance Computing, Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"Agency for Science Technology and Research (A*STAR), Centre for Frontier AI Research, Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4675-7055","authenticated-orcid":false,"given":"Joey Tianyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Agency for Science Technology and Research (A*STAR), Centre for Frontier AI Research, Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9116-1595","authenticated-orcid":false,"given":"Rick","family":"Goh","sequence":"additional","affiliation":[{"name":"Agency for Science Technology and Research (A*STAR), Institute of High Performance Computing, Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref5","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","volume-title":"arXiv:1806.08342","author":"Krishnamoorthi","year":"2018"},{"key":"ref6","article-title":"Robust quantization: One model to rule them all","volume-title":"arXiv:2002.07686","author":"Shkolnik","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref8","article-title":"Towards efficient training for neural network quantization","volume-title":"arXiv:1912.10207","author":"Jin","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/math9172144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref12","article-title":"Ternary weight networks","volume-title":"arXiv:1605.04711","author":"Li","year":"2016"},{"key":"ref13","article-title":"BinaryBERT: Pushing the limit of BERT quantization","volume-title":"arXiv:2012.15701","author":"Bai","year":"2020"},{"key":"ref14","article-title":"BinaryDuo: Reducing gradient mismatch in binary activation network by coupling binary activations","volume-title":"arXiv:2002.06517","author":"Kim","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref18","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","volume-title":"arXiv:1606.06160","author":"Zhou","year":"2016"},{"key":"ref19","article-title":"Mixed precision training","volume-title":"arXiv:1710.03740","author":"Micikevicius","year":"2017"},{"key":"ref20","article-title":"Scalable methods for 8-bit training of neural networks","volume-title":"arXiv:1805.11046","author":"Banner","year":"2018"},{"key":"ref21","article-title":"Training and inference with integers in deep neural networks","volume-title":"arXiv:1802.04680","author":"Wu","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.027"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref24","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"arXiv:2101.01321","author":"Kim","year":"2021"},{"key":"ref25","article-title":"Mixed precision quantization of convnets via differentiable neural architecture search","volume-title":"arXiv:1812.00090","author":"Wu","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2021.3120068"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172941"},{"key":"ref35","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"arXiv:1510.00149","author":"Han","year":"2015"},{"key":"ref36","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"arXiv:1803.03635","author":"Frankle","year":"2018"},{"key":"ref37","article-title":"Sparse networks from scratch: Faster training without losing performance","volume-title":"arXiv:1907.04840","author":"Dettmers","year":"2019"},{"key":"ref38","article-title":"The state of sparsity in deep neural networks","volume-title":"arXiv:1902.09574","author":"Gale","year":"2019"},{"key":"ref39","article-title":"Rethinking the value of network pruning","volume-title":"arXiv:1810.05270","author":"Liu","year":"2018"},{"key":"ref40","article-title":"A survey of FPGA-based neural network accelerator","volume-title":"arXiv:1712.08934","author":"Guo","year":"2017"},{"key":"ref41","article-title":"Low-memory neural network training: A technical report","volume-title":"arXiv:1904.10631","author":"Sohoni","year":"2019"},{"key":"ref42","article-title":"Knowledge distillation: A survey","volume-title":"arXiv:2006.05525","author":"Gou","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_45"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021727"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00185"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.04.005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1201\/9781315161532"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"issue":"1","key":"ref49","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref51","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref52","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref56","article-title":"Attention is all you need","volume-title":"arXiv:1706.03762","author":"Vaswani","year":"2017"},{"key":"ref57","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref60","article-title":"CNN-based density estimation and crowd counting: A survey","volume-title":"arXiv:2003.12783","author":"Gao","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299097"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248013"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974830"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00192"},{"key":"ref67","first-page":"1","article-title":"Precision gating: Improving neural network efficiency with dynamic dual-precision activations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref68","first-page":"1","article-title":"Ultra-low precision 4-bit training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sun"},{"key":"ref69","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"arXiv:1811.06965","author":"Huang","year":"2018"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10422842\/09865979.pdf?arnumber=9865979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:08:49Z","timestamp":1708110529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9865979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":69,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3190451","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}