{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:58:33Z","timestamp":1791914313139,"version":"4.3.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Development Program of Guangdong Province of China","award":["2019B010120001"],"award-info":[{"award-number":["2019B010120001"]}]},{"name":"Key Research and Development Project of Zhejiang Province","award":["2019C01004"],"award-info":[{"award-number":["2019C01004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tnnls.2020.2980041","type":"journal-article","created":{"date-parts":[[2020,4,3]],"date-time":"2020-04-03T20:00:24Z","timestamp":1585944024000},"page":"1067-1081","source":"Crossref","is-referenced-by-count":34,"title":["A Learning Framework for <i>n<\/i>-Bit Quantized Neural Networks Toward FPGAs"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6568-8801","authenticated-orcid":false,"given":"Jun","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7910-810X","authenticated-orcid":false,"given":"Liang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1251-2129","authenticated-orcid":false,"given":"Xianfang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","article-title":"Striving for simplicity: The all convolutional net","author":"tobias springenberg","year":"2014","journal-title":"arXiv 1412 6806"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref31","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.64"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009"},{"key":"ref36","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref34","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref28","article-title":"Trained ternary quantization","author":"zhu","year":"2016","journal-title":"arXiv 1612 01064"},{"key":"ref27","article-title":"DoReFa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"arXiv 1606 06160 [cs]"},{"key":"ref29","article-title":"Precision highway for ultra low-precision quantization","author":"park","year":"2018","journal-title":"arXiv 1812 09818"},{"key":"ref2","first-page":"1","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref20","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref22","article-title":"Bridging the accuracy gap for 2-bit quantized neural networks (QNN)","author":"choi","year":"2018","journal-title":"arXiv 1807 06964"},{"key":"ref21","first-page":"382","article-title":"On the construction of Huffman trees","author":"van leeuwen","year":"1976","journal-title":"Proc ICALP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref23","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018","journal-title":"arXiv 1805 06085"},{"key":"ref26","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"zhou","year":"2017","journal-title":"arXiv 1702 03044"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref50","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":"ref51","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","article-title":"FractalNet: Ultra-deep neural networks without residuals","author":"larsson","year":"2016","journal-title":"arXiv 1605 07648"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ReConFig.2016.7857144"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2009.25"},{"key":"ref15","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016","journal-title":"arXiv 1602 02830 [cs]"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref3","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2015","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref7","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2014","journal-title":"arXiv 1412 7062"},{"key":"ref49","author":"gross","year":"2016","journal-title":"Training and investigating residual nets"},{"key":"ref9","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref45","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","author":"sermanet","year":"2012","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref48","article-title":"Ternary weight networks","author":"li","year":"2016","journal-title":"arXiv 1605 04711 [cs]"},{"key":"ref47","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"5","article-title":"Reading digits in natural images with unsupervised feature learning","volume":"2011","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref41","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2014","journal-title":"arXiv 1412 6550"},{"key":"ref44","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"arXiv 1302 4389"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9365681\/09056829.pdf?arnumber=9056829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:08Z","timestamp":1652194388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9056829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":53,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2980041","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}