{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T21:26:47Z","timestamp":1776202007345,"version":"3.50.1"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>In this article, we present a low-energy inference method for convolutional neural networks in image classification applications. The lower energy consumption is achieved by using a highly pruned (lower-energy) network if the resulting network can provide a correct output. More specifically, the proposed inference method makes use of two pruned neural networks (NNs), namely mildly and aggressively pruned networks, which are both designed offline. In the system, a third NN makes use of the input data for the online selection of the appropriate pruned network. The third network, for its feature extraction, employs the same convolutional layers as those of the aggressively pruned NN, thereby reducing the overhead of the online management. There is some accuracy loss induced by the proposed method where, for a given level of accuracy, the energy gain of the proposed method is considerably larger than the case of employing any one pruning level. The proposed method is independent of both the pruning method and the network architecture. The efficacy of the proposed inference method is assessed on Eyeriss hardware accelerator platform for some of the state-of-the-art NN architectures. Our studies show that this method may provide, on average, 70% energy reduction compared to the original NN at the cost of about 3% accuracy loss on the CIFAR-10 dataset.<\/jats:p>","DOI":"10.1145\/3460972","type":"journal-article","created":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T17:39:23Z","timestamp":1627839563000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["An Energy-Efficient Inference Method in Convolutional Neural Networks Based on Dynamic Adjustment of the Pruning Level"],"prefix":"10.1145","volume":"26","author":[{"given":"Mohammad-Ali","family":"Maleki","sequence":"first","affiliation":[{"name":"University of Tehran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alireza","family":"Nabipour-Meybodi","sequence":"additional","affiliation":[{"name":"University of Tehran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Kamal","sequence":"additional","affiliation":[{"name":"University of Tehran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Afzali-Kusha","sequence":"additional","affiliation":[{"name":"University of Tehran and Institute for Research in Fundamental Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massoud","family":"Pedram","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_2_1_2_1","volume-title":"Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 7639","author":"Esteva Andre","year":"2017","unstructured":"Andre Esteva , Brett Kuprel , Roberto A. Novoa , Justin Ko , Susan M. Swetter , Helen M. Blau , and Sebastian Thrun . 2017. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 7639 ( 2017 ), 115\u2013118. Andre Esteva, Brett Kuprel, Roberto A. Novoa, Justin Ko, Susan M. Swetter, Helen M. Blau, and Sebastian Thrun. 2017. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 7639 (2017), 115\u2013118."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969173"},{"key":"e_1_2_1_5_1","unstructured":"NVIDIA. 2015. GPU-Based Deep Learning Inference: A Performance and Power Analysis. White Paper. NVIDIA.  NVIDIA. 2015. GPU-Based Deep Learning Inference: A Performance and Power Analysis. White Paper. NVIDIA."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130424"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67952-5_2"},{"key":"e_1_2_1_10_1","unstructured":"S. Han H. Mao and W. J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning trained quantization and Huffman coding. arXiv:1510.00149.  S. Han H. Mao and W. J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning trained quantization and Huffman coding. arXiv:1510.00149."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_2_1_12_1","unstructured":"S. Zhou Y. Wu Z. Ni X. Zhou H. Wen and Y. Zou. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160.  S. Zhou Y. Wu Z. Ni X. Zhou H. Wen and Y. Zou. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_2_1_14_1","unstructured":"Aojun Zhou Anbang Yao Yiwen Guo Lin Xu and Yurong Chen. 2017. Incremental network quantization: Towards lossless CNNs with low-precision weights. arXiv:1702.03044.  Aojun Zhou Anbang Yao Yiwen Guo Lin Xu and Yurong Chen. 2017. Incremental network quantization: Towards lossless CNNs with low-precision weights. arXiv:1702.03044."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130482"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2742698"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/109230.109298"},{"key":"e_1_2_1_18_1","first-page":"109","article-title":"Neuronal mechanisms of developmental plasticity in the cat's visual system","volume":"3","author":"Rauschecker J. P.","year":"1984","unstructured":"J. P. Rauschecker . 1984 . Neuronal mechanisms of developmental plasticity in the cat's visual system . Human Neurobiology 3 , 2 (1984), 109 \u2013 114 . J. P. Rauschecker. 1984. Neuronal mechanisms of developmental plasticity in the cat's visual system. Human Neurobiology 3, 2 (1984), 109\u2013114.","journal-title":"Human Neurobiology"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/502172a"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627613"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062307"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195664"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"e_1_2_1_26_1","unstructured":"Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient transfer learning. arXiv:1611.06440.  Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient transfer learning. arXiv:1611.06440."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence.","author":"Ding Xiaohan","year":"2018","unstructured":"Xiaohan Ding , Guiguang Ding , Jungong Han , and Sheng Tang . 2018 . Auto-balanced filter pruning for efficient convolutional neural networks . In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Xiaohan Ding, Guiguang Ding, Jungong Han, and Sheng Tang. 2018. Auto-balanced filter pruning for efficient convolutional neural networks. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence."},{"key":"e_1_2_1_29_1","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2016. Pruning filters for efficient ConvNets. arXiv:1608.08710.  Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2016. Pruning filters for efficient ConvNets. arXiv:1608.08710."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2830840.2830854"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007192"},{"key":"e_1_2_1_32_1","volume-title":"Weinberger","author":"Huang Gao","year":"2017","unstructured":"Gao Huang , Danlu Chen , Tianhong Li , Felix Wu , Laurens van der Maaten , and Kilian Q . Weinberger . 2017 . Multi-scale de nse networks for resource efficient image classification. arXiv:1703.09844. Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Multi-scale dense networks for resource efficient image classification. arXiv:1703.09844."},{"key":"e_1_2_1_33_1","unstructured":"Jiahui Yu Linjie Yang Ning Xu Jianchao Yang and Thomas Huang. 2018. Slimmable neural networks. arXiv:1812.08928.  Jiahui Yu Linjie Yang Ning Xu Jianchao Yang and Thomas Huang. 2018. Slimmable neural networks. arXiv:1812.08928."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294979"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2830840.2830854"},{"key":"e_1_2_1_36_1","volume-title":"Deep neural network energy estimation tool. Retrieved","author":"MIT.","year":"2021","unstructured":"MIT. 2017. Deep neural network energy estimation tool. Retrieved June 4, 2021 from https:\/\/energyestimation.mit.edu. MIT. 2017. Deep neural network energy estimation tool. Retrieved June 4, 2021 from https:\/\/energyestimation.mit.edu."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460972","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:22Z","timestamp":1750193302000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3460972"],"URL":"https:\/\/doi.org\/10.1145\/3460972","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}