{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:41Z","timestamp":1740108041011,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T00:00:00Z","timestamp":1630195200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T00:00:00Z","timestamp":1630195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072165","U19A2058"],"award-info":[{"award-number":["62072165","U19A2058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Research Projects of Zhejiang Lab","award":["2020KE0AB01"],"award-info":[{"award-number":["2020KE0AB01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s00521-021-06433-5","type":"journal-article","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T19:02:15Z","timestamp":1630263735000},"page":"757-769","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EPMC: efficient parallel memory compression in deep neural network training"],"prefix":"10.1007","volume":"34","author":[{"given":"Zailong","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chubo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,29]]},"reference":[{"issue":"7553","key":"6433_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"6433_CR2","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT press Cambridge, Cambridge"},{"key":"6433_CR3","unstructured":"Bojarski M, Del\u00a0Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang J, et\u00a0al., End to end learning for self-driving cars, arXiv preprint arXiv:1604.07316"},{"key":"6433_CR4","doi-asserted-by":"crossref","unstructured":"Sun Y, Wang X, Tang X (2013) Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3476\u20133483","DOI":"10.1109\/CVPR.2013.446"},{"issue":"1","key":"6433_CR5","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.cirp.2016.04.072","volume":"65","author":"D Weimer","year":"2016","unstructured":"Weimer D, Scholz-Reiter B, Shpitalni M (2016) Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. CIRP Ann 65(1):417\u2013420","journal-title":"CIRP Ann"},{"key":"6433_CR6","unstructured":"Kalchbrenner N, Grefenstette E, Blunsom P, A convolutional neural network for modelling sentences, arXiv preprint arXiv:1404.2188"},{"key":"6433_CR7","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"6433_CR8","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"6433_CR9","unstructured":"LeCun Y, et\u00a0al (2015) Lenet-5, convolutional neural networks. URL: http:\/\/yann.lecun.com\/exdb\/lenet 20(5): 14"},{"key":"6433_CR10","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":"6433_CR11","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097\u20131105"},{"key":"6433_CR12","unstructured":"Simonyan K, Zisserman A, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6433_CR13","doi-asserted-by":"crossref","unstructured":"Rhu M, Gimelshein N, Clemons J, Zulfiqar A, Keckler S (2016) vdnn: Virtualized deep neural networks for scalable, memory-efficient neural network design. Memory-Efficient Neural Network Design, MICRO-2016","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"6433_CR14","doi-asserted-by":"crossref","unstructured":"Rhu M, O\u2019Connor M, Chatterjee N, Pool J, Kwon Y, Keckler SW, Compressing dma engine: leveraging activation sparsity for training deep neural networks. In: (2018) IEEE International symposium on high performance computer architecture (HPCA). IEEE 2018:78\u201391","DOI":"10.1109\/HPCA.2018.00017"},{"key":"6433_CR15","unstructured":"Han S, Mao H, Dally WJ, Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149"},{"key":"6433_CR16","doi-asserted-by":"crossref","unstructured":"He Y, Lin J,\u00a0Liu Z,Wang H, Li L-J,\u00a0Han S (2018) Amc: automl for model compression and acceleration on mobile devices. In: Proceedings of the European conference on computer vision (ECCV), pp. 784\u2013800","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"6433_CR17","doi-asserted-by":"crossref","unstructured":"Guo S,\u00a0Wang Y,\u00a0Li Q,\u00a0Yan J (2020) Dmcp: Differentiable markov channel pruning for neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 1539\u20131547","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"6433_CR18","doi-asserted-by":"crossref","unstructured":"Li Y,\u00a0Gu S,\u00a0Mayer C, Gool LV,\u00a0Timofte R (2020) Group sparsity: the hinge between filter pruning and decomposition for network compression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8018\u20138027","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"6433_CR19","doi-asserted-by":"crossref","unstructured":"Lin M,\u00a0Ji R,\u00a0Wang Y,\u00a0Zhang Y,\u00a0Zhang B,\u00a0Tian Y,\u00a0Shao L (2020) Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 1529\u20131538","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"6433_CR20","doi-asserted-by":"crossref","unstructured":"Liu Z,\u00a0Mu H,\u00a0Zhang X,\u00a0Guo Z,\u00a0Yang X, Cheng K-T,\u00a0Sun J (2019) Metapruning: Meta learning for automatic neural network channel pruning. In: Proceedings of the IEEE international conference on computer vision, pp. 3296\u20133305","DOI":"10.1109\/ICCV.2019.00339"},{"key":"6433_CR21","unstructured":"Neill JO, An overview of neural network compression. arXiv preprint arXiv:2006.03669"},{"key":"6433_CR22","unstructured":"An overview of model compression techniques for deep learning in space. https:\/\/medium.com\/gsi-technology\/an-overview-of-model-compression-techniques-for-deep-learning-in-space-3fd8d4ce84e5 (2020)"},{"key":"6433_CR23","doi-asserted-by":"crossref","unstructured":"Xu Y,\u00a0Wang Y,\u00a0Zhou A,\u00a0Lin W,\u00a0Xiong H (2018) Deep neural network compression with single and multiple level quantization. In: Proceedings of the AAAI conference on artificial intelligence. 32","DOI":"10.1609\/aaai.v32i1.11663"},{"key":"6433_CR24","doi-asserted-by":"crossref","unstructured":"Kim H, Khan MUK, Kyung C-M (2019) Efficient neural network compression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 12569\u201312577","DOI":"10.1109\/CVPR.2019.01285"},{"key":"6433_CR25","doi-asserted-by":"crossref","unstructured":"Ge S (2018) Efficient deep learning in network compression and acceleration. In: Digital systems, IntechOpen","DOI":"10.5772\/intechopen.79562"},{"key":"6433_CR26","doi-asserted-by":"crossref","unstructured":"Paupamah K, James S, Klein R (2020) Quantisation and pruning for neural network compression and regularisation. In: International SAUPEC\/RobMech\/PRASA Conference. IEEE 2020:1\u20136","DOI":"10.1109\/SAUPEC\/RobMech\/PRASA48453.2020.9041096"},{"key":"6433_CR27","doi-asserted-by":"crossref","unstructured":"Jin S, Di S,\u00a0Liang X,\u00a0Tian J,\u00a0Tao D,\u00a0Cappello F (2019) Deepsz: A novel framework to compress deep neural networks by using error-bounded lossy compression. In: Proceedings of the 28th international symposium on high-performance parallel and distributed computing. pp. 159\u2013170","DOI":"10.1145\/3307681.3326608"},{"key":"6433_CR28","unstructured":"Kozlov A,\u00a0Lazarevich I,\u00a0Shamporov V,\u00a0Lyalyushkin N,\u00a0Gorbachev Y, Neural network compression framework for fast model inference. arXiv preprint arXiv:2002.08679"},{"key":"6433_CR29","unstructured":"Goyal P,\u00a0Doll\u00e1r P,\u00a0Girshick R,\u00a0Noordhuis P,\u00a0Wesolowski L,\u00a0Kyrola A,\u00a0Tulloch A,\u00a0Jia Y,\u00a0He K, Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677"},{"key":"6433_CR30","doi-asserted-by":"crossref","unstructured":"Jain A, Phanishayee A, Mars J, Tang L, Pekhimenko G (2018) Gist: Efficient data encoding for deep neural network training. In: ACM\/IEEE 45th annual international symposium on computer architecture (ISCA). IEEE 2018:776\u2013789","DOI":"10.1109\/ISCA.2018.00070"},{"key":"6433_CR31","unstructured":"Chen T,\u00a0Xu B,\u00a0Zhang C,\u00a0Guestrin C, Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174"},{"key":"6433_CR32","doi-asserted-by":"crossref","unstructured":"Wen W, Xu C,\u00a0Wu C,\u00a0Wang Y,\u00a0Chen Y,\u00a0Li H (2017) Coordinating filters for faster deep neural networks. In: Proceedings of the IEEE international conference on computer vision. pp. 658\u2013666","DOI":"10.1109\/ICCV.2017.78"},{"key":"6433_CR33","unstructured":"Zhu C,\u00a0Han S,\u00a0Mao H, Dally WJ, Trained ternary quantization. arXiv preprint arXiv:1612.01064"},{"key":"6433_CR34","doi-asserted-by":"crossref","unstructured":"Liu Z,\u00a0Wu B,\u00a0Luo W,\u00a0Yang X,\u00a0Liu W, Cheng K-T (2018) Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm. In: Proceedings of the European conference on computer vision (ECCV), pp. 722\u2013737","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"6433_CR35","doi-asserted-by":"crossref","unstructured":"Qin H,\u00a0Gong R,\u00a0Liu X,\u00a0Shen M,\u00a0Wei Z,\u00a0Yu F,\u00a0Song J (2020) Forward and backward information retention for accurate binary neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 2250\u20132259","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"6433_CR36","unstructured":"Sermanet P,\u00a0Eigen D,\u00a0Zhang X,\u00a0Mathieu M,\u00a0Fergus R,\u00a0LeCun Y, Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229"},{"key":"6433_CR37","doi-asserted-by":"crossref","unstructured":"Szegedy C,\u00a0Liu W,\u00a0Jia Y,\u00a0Sermanet P,\u00a0Reed S,\u00a0Anguelov D,\u00a0Erhan D,\u00a0Vanhoucke V,\u00a0Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6433_CR38","doi-asserted-by":"crossref","unstructured":"De\u00a0Sa C,\u00a0Feldman M,\u00a0R\u00e9 C,\u00a0Olukotun K (2017) Understanding and optimizing asynchronous low-precision stochastic gradient descent. In: Proceedings of the 44th annual international symposium on computer architecture, pp. 561\u2013574","DOI":"10.1145\/3079856.3080248"},{"key":"6433_CR39","volume-title":"Professional CUDA c programming","author":"J Cheng","year":"2014","unstructured":"Cheng J, Grossman M, McKercher T (2014) Professional CUDA c programming. Wiley, Hoboken"},{"key":"6433_CR40","unstructured":"Nvidia kepler architecture (2012) https:\/\/www.nvidia.cn\/content\/apac\/pdf\/tesla\/nvidia-kepler-gk110-architecture-whitepaper-cn.pdf"},{"key":"6433_CR41","unstructured":"Nvidia tesla k40c (2013) https:\/\/www.techpowerup.com\/gpu-specs\/tesla-k40c.c2505"},{"key":"6433_CR42","unstructured":"Nvidia geforce gtx 1070 (2016) https:\/\/www.nvidia.com\/en-in\/geforce\/products\/10series\/geforce-gtx-1070\/"},{"issue":"3","key":"6433_CR43","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211\u2013252","journal-title":"Int J Comput Vision"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06433-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06433-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06433-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T07:37:55Z","timestamp":1673163475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06433-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,29]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["6433"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06433-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,8,29]]},"assertion":[{"value":"4 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}