{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:27:41Z","timestamp":1779294461721,"version":"3.51.4"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T00:00:00Z","timestamp":1639699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T00:00:00Z","timestamp":1639699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Recent advances in deep neural networks have achieved higher accuracy with more complex models. Nevertheless, they require much longer training time. To reduce the training time, training methods using quantized weight, activation, and gradient have been proposed. Neural network calculation by integer format improves the energy efficiency of hardware for deep learning models. Therefore, training methods for deep neural networks with fixed point format have been proposed. However, the narrow data representation range of the fixed point format degrades neural network accuracy. In this work, we propose a new fixed point format named shifted dynamic fixed point (S-DFP) to prevent accuracy degradation in quantized neural networks training. S-DFP can change the data representation range of dynamic fixed point format by adding bias to the exponent. We evaluated the effectiveness of S-DFP for quantized neural network training on the ImageNet task using ResNet-34, ResNet-50, ResNet-101 and ResNet-152. For example, the accuracy of quantized ResNet-152 is improved from 76.6% with conventional 8-bit DFP to 77.6% with 8-bit S-DFP.<\/jats:p>","DOI":"10.1007\/s00521-021-06821-x","type":"journal-article","created":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T18:20:37Z","timestamp":1639765237000},"page":"535-542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["S-DFP: shifted dynamic fixed point for quantized deep neural network training"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7135-9449","authenticated-orcid":false,"given":"Yasufumi","family":"Sakai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutaka","family":"Tamiya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,17]]},"reference":[{"key":"6821_CR1","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"6821_CR2","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6821_CR3","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6821_CR4","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"6821_CR5","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y, Berg A C (2016) SSD: Single Shot Multibox Detector. In European conference on computer vision, pp. 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6821_CR6","unstructured":"Zhou S, Wu Y, Ni Z, Zhou X, Wen H, Zou Y (2016) DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160"},{"key":"6821_CR7","doi-asserted-by":"crossref","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) XNOR-Net: Imagenet classification using binary convolutional neural networks. In European conference on computer vision, pp. 525\u2013542","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"6821_CR8","unstructured":"Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, Wu, H (2017) Mixed precision training. arXiv preprint arXiv:1710.03740"},{"key":"6821_CR9","doi-asserted-by":"crossref","unstructured":"Chen C Y, Choi J, Gopalakrishnan K, Srinivasan V, Venkataramani S (2018) Exploiting approximate computing for deep learning acceleration. In: 2018 Design, automation and test in Europe conference and exhibition, pp. 821\u2013826","DOI":"10.23919\/DATE.2018.8342119"},{"key":"6821_CR10","unstructured":"Wang N, Choi J, Brand D, Chen C Y, Gopalakrishnan K (2018) Training deep neural networks with 8-bit floating point numbers. arXiv preprint arXiv:1812.08011"},{"key":"6821_CR11","first-page":"4900","volume":"32","author":"X Sun","year":"2019","unstructured":"Sun X, Choi J, Chen CY, Wang N, Venkataramani S, Srinivasan V, Cui X, Zhang W, Gopalakrishnan K (2019) Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks. Adv Neural Inf Process Syst 32:4900\u20134909","journal-title":"Adv Neural Inf Process Syst"},{"key":"6821_CR12","doi-asserted-by":"crossref","unstructured":"Horowitz M (2014) Computing\u2019s energy problem (and what we can do about it). In: IEEE International solid-state circuits conference digest of technical papers, pp. 10\u201314","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"6821_CR13","unstructured":"Das D, Mellempudi N, Mudigere D, Kalamkar D, Avancha S, Banerjee K, Sridharan S, Vaidyanathan K, Kaul B, Georganas E, Heinecke A, Dubey P, Corbal J, Shustrov N, Dubtsov R, Fomenko E, Pirogov V. (2018) Mixed precision training of convolutional neural networks using integer operations. arXiv preprint arXiv:1802.00930"},{"key":"6821_CR14","unstructured":"Wu S, Li G, Chen F, Shi L (2018) Training and inference with integers in deep neural networks. arXiv preprint arXiv:1802.04680"},{"key":"6821_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6821_CR16","unstructured":"Gupta S, Agrawal A, Gopalakrishnan K, Narayanan P (2015) Deep learning with limited numerical precision. In: International conference on machine learning, pp. 1737\u20131746"},{"key":"6821_CR17","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neunet.2019.12.027","volume":"125","author":"Y Yang","year":"2020","unstructured":"Yang Y, Deng L, Wu S, Yan T, Xie Y, Li G (2020) Training high-performance and large-scale deep neural networks with full 8-bit integers. Neural Netw 125:70\u201382","journal-title":"Neural Netw"},{"key":"6821_CR18","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv preprint arXiv:1706.03762"},{"key":"6821_CR19","unstructured":"Devlin J, Chang M W, Lee K, Toutanova K (2018) BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06821-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06821-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06821-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T18:28:57Z","timestamp":1737656937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06821-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,17]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6821"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06821-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,17]]},"assertion":[{"value":"2 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}