{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T17:35:23Z","timestamp":1768325723507,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":182,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T00:00:00Z","timestamp":1592179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CNS-1816213, CNS-1704469"],"award-info":[{"award-number":["CNS-1816213, CNS-1704469"]}]},{"name":"NIH","award":["1R01LM013329-01"],"award-info":[{"award-number":["1R01LM013329-01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,15]]},"DOI":"10.1145\/3386901.3388947","type":"proceedings-article","created":{"date-parts":[[2020,6,7]],"date-time":"2020-06-07T01:27:30Z","timestamp":1591493250000},"page":"175-190","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Fast and scalable in-memory deep multitask learning via neural weight virtualization"],"prefix":"10.1145","author":[{"given":"Seulki","family":"Lee","sequence":"first","affiliation":[{"name":"University of North Carolina at Chapel Hill"}]},{"given":"Shahriar","family":"Nirjon","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill"}]}],"member":"320","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16). 265--283.","author":"Abadi Mart\u00edn","year":"2016"},{"key":"e_1_3_2_1_2_1","volume-title":"Structural compression of convolutional neural networks based on greedy filter pruning. arXiv preprint arXiv:1705.07356","author":"Abbasi-Asl Reza","year":"2017"},{"key":"e_1_3_2_1_3_1","unstructured":"Arvind Agarwal Samuel Gerber and Hal Daume. 2010. Learning multiple tasks using manifold regularization. In Advances in neural information processing systems. 46--54.  Arvind Agarwal Samuel Gerber and Hal Daume. 2010. Learning multiple tasks using manifold regularization. In Advances in neural information processing systems. 46--54."},{"key":"e_1_3_2_1_4_1","unstructured":"Shun-ichi Amari. 1997. Neural learning in structured parameter spaces-natural Riemannian gradient. In Advances in neural information processing systems. 127--133.  Shun-ichi Amari. 1997. Neural learning in structured parameter spaces-natural Riemannian gradient. In Advances in neural information processing systems. 127--133."},{"key":"e_1_3_2_1_5_1","volume-title":"Natural gradient works efficiently in learning. Neural computation 10, 2","author":"Amari Shun-Ichi","year":"1998"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.125867"},{"key":"e_1_3_2_1_7_1","unstructured":"Amazon. 2019. Introducing Alexa Voice Service Integration for AWS IoT Core a new way to cost-effectively bring Alexa Voice to any type of connected device. https:\/\/aws.amazon.com\/blogs\/iot\/introducing-alexa-voice-service-integration-for-aws-iot-core\/.  Amazon. 2019. Introducing Alexa Voice Service Integration for AWS IoT Core a new way to cost-effectively bring Alexa Voice to any type of connected device. https:\/\/aws.amazon.com\/blogs\/iot\/introducing-alexa-voice-service-integration-for-aws-iot-core\/."},{"key":"e_1_3_2_1_8_1","volume-title":"hear, and read: Deep aligned representations. arXiv preprint arXiv:1706.00932","author":"Aytar Yusuf","year":"2017"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0043-y"},{"key":"e_1_3_2_1_10_1","first-page":"37","article-title":"Non-preemptive multitasking","volume":"30","author":"Bartel Joe","year":"2011","journal-title":"Comput. J."},{"key":"e_1_3_2_1_11_1","unstructured":"Aviad Barzilai and Koby Crammer. 2015. Convex multi-task learning by clustering. In Artificial Intelligence and Statistics. 65--73.  Aviad Barzilai and Koby Crammer. 2015. Convex multi-task learning by clustering. In Artificial Intelligence and Statistics. 65--73."},{"key":"e_1_3_2_1_12_1","volume-title":"Machine learning 28, 1","author":"Baxter Jonathan","year":"1997"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.738305"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980058"},{"key":"e_1_3_2_1_16_1","volume-title":"Davide Del Testa","author":"Bojarski Mariusz","year":"2016"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_3_2_1_19_1","volume-title":"Multitask learning. Machine learning 28, 1","author":"Caruana Rich","year":"1997"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2381119"},{"key":"e_1_3_2_1_21_1","unstructured":"Guobin Chen Wongun Choi Xiang Yu Tony Han and Manmohan Chandraker. 2017. Learning efficient object detection models with knowledge distillation. In Advances in Neural Information Processing Systems. 742--751.  Guobin Chen Wongun Choi Xiang Yu Tony Han and Manmohan Chandraker. 2017. Learning efficient object detection models with knowledge distillation. In Advances in Neural Information Processing Systems. 742--751."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553392"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2006.08.018"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. 2285--2294","author":"Chen Wenlin","year":"2015"},{"key":"e_1_3_2_1_26_1","volume-title":"Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs. arXiv e-prints, Article arXiv:1802.10280 (Feb","author":"Chen Xuhao","year":"2018"},{"key":"e_1_3_2_1_27_1","volume-title":"A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282","author":"Cheng Yu","year":"2017"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.327"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00220"},{"key":"e_1_3_2_1_30_1","volume-title":"Unifying and merging well-trained deep neural networks for inference stage. arXiv preprint arXiv:1805.04980","author":"Chou Yi-Min","year":"2018"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2009.10.017"},{"key":"e_1_3_2_1_32_1","unstructured":"ARM Cortex. 2004. M3 Processor. Cortex-M Series (2004).  ARM Cortex. 2004. M3 Processor. Cortex-M Series (2004)."},{"key":"e_1_3_2_1_33_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016"},{"key":"e_1_3_2_1_34_1","unstructured":"Cypress. 2017. CY15B104Q. http:\/\/www.cypress.com\/file\/209146\/download.  Cypress. 2017. CY15B104Q. http:\/\/www.cypress.com\/file\/209146\/download."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09.  J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"e_1_3_2_1_37_1","unstructured":"Eleazar Eskin Alex J Smola and SVN Vishwanathan. 2004. Laplace propagation. In Advances in Neural Information Processing Systems. 441--448.  Eleazar Eskin Alex J Smola and SVN Vishwanathan. 2004. Laplace propagation. In Advances in Neural Information Processing Systems. 441--448."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_3_2_1_39_1","volume-title":"Catastrophic forgetting in connectionist networks. Trends in cognitive sciences 3, 4","author":"French Robert M","year":"1999"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0107-58"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"e_1_3_2_1_42_1","volume-title":"Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems. arXiv preprint arXiv:1810.07751","author":"Gobieski Graham","year":"2018"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304011"},{"key":"e_1_3_2_1_44_1","volume-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211","author":"Goodfellow Ian J","year":"2013"},{"key":"e_1_3_2_1_45_1","unstructured":"Google. 2019. Face Match on Google Nest Hub Max. https:\/\/support.google.com\/googlenest\/answer\/9320885?hl=en.  Google. 2019. Face Match on Google Nest Hub Max. https:\/\/support.google.com\/googlenest\/answer\/9320885?hl=en."},{"key":"e_1_3_2_1_46_1","unstructured":"Google. 2019. FAQs on camera sensing: Google Nest Hub Max. https:\/\/support.google.com\/googlenest\/answer\/9449279?hl=en.  Google. 2019. FAQs on camera sensing: Google Nest Hub Max. https:\/\/support.google.com\/googlenest\/answer\/9449279?hl=en."},{"key":"e_1_3_2_1_47_1","unstructured":"Google. 2019. Introducing Google Nest Hub. https:\/\/support.google.com\/googlenest\/answer\/9136909?hl=en.  Google. 2019. Introducing Google Nest Hub. https:\/\/support.google.com\/googlenest\/answer\/9136909?hl=en."},{"key":"e_1_3_2_1_48_1","unstructured":"Google. 2019. Learn about familiar face detection and how to manage your library. https:\/\/support.google.com\/googlenest\/answer\/9268625?co=GENIE.Platform%3DAndroid&hl=en.  Google. 2019. Learn about familiar face detection and how to manage your library. https:\/\/support.google.com\/googlenest\/answer\/9268625?co=GENIE.Platform%3DAndroid&hl=en."},{"key":"e_1_3_2_1_49_1","unstructured":"Google. 2019. TensorFlow Lite for Microcontrollers. https:\/\/www.tensorflow.org\/lite\/microcontrollers.  Google. 2019. TensorFlow Lite for Microcontrollers. https:\/\/www.tensorflow.org\/lite\/microcontrollers."},{"key":"e_1_3_2_1_50_1","unstructured":"Google. 2019. Voice Match and media on Google Nest and Google Home speakers and displays. https:\/\/support.google.com\/googlenest\/answer\/7342711?hl=en.  Google. 2019. Voice Match and media on Google Nest and Google Home speakers and displays. https:\/\/support.google.com\/googlenest\/answer\/7342711?hl=en."},{"key":"e_1_3_2_1_51_1","unstructured":"Yiwen Guo Anbang Yao and Yurong Chen. 2016. Dynamic network surgery for efficient dnns. In Advances In Neural Information Processing Systems. 1379--1387.  Yiwen Guo Anbang Yao and Yurong Chen. 2016. Dynamic network surgery for efficient dnns. In Advances In Neural Information Processing Systems. 1379--1387."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886688"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016128"},{"key":"e_1_3_2_1_54_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015"},{"key":"e_1_3_2_1_55_1","unstructured":"Song Han Jeff Pool John Tran and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in neural information processing systems. 1135--1143.  Song Han Jeff Pool John Tran and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in neural information processing systems. 1135--1143."},{"key":"e_1_3_2_1_56_1","unstructured":"Babak Hassibi and David G Stork. 1993. Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems. 164--171.  Babak Hassibi and David G Stork. 1993. Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information processing systems. 164--171."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI.2016.0038"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853595"},{"key":"e_1_3_2_1_60_1","unstructured":"Xiaoxi He Zimu Zhou and Lothar Thiele. 2018. Multi-task zipping via layerwise neuron sharing. In Advances in Neural Information Processing Systems. 6016--6026.  Xiaoxi He Zimu Zhou and Lothar Thiele. 2018. Multi-task zipping via layerwise neuron sharing. In Advances in Neural Information Processing Systems. 6016--6026."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/11813040_1"},{"key":"e_1_3_2_1_63_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015"},{"key":"e_1_3_2_1_64_1","volume-title":"Raspberry Pi Architecture","author":"Holton Jon","year":"2012"},{"key":"e_1_3_2_1_65_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017"},{"key":"e_1_3_2_1_66_1","unstructured":"Gary B Huang Marwan Mattar Tamara Berg and Eric Learned-Miller. 2008. Labeled faces in the wild: A database forstudying face recognition in unconstrained environments.  Gary B Huang Marwan Mattar Tamara Berg and Eric Learned-Miller. 2008. Labeled faces in the wild: A database forstudying face recognition in unconstrained environments."},{"key":"e_1_3_2_1_67_1","unstructured":"Texas Instrument. 2018. MSP EnergyTrace Technology. http:\/\/www.ti.com\/tool\/ENERGYTRACE  Texas Instrument. 2018. MSP EnergyTrace Technology. http:\/\/www.ti.com\/tool\/ENERGYTRACE"},{"key":"e_1_3_2_1_68_1","volume-title":"Training cnns with low-rank filters for efficient image classification. arXiv preprint arXiv:1511.06744","author":"Ioannou Yani","year":"2015"},{"key":"e_1_3_2_1_69_1","volume-title":"One model to learn them all. arXiv preprint arXiv:1706.05137","author":"Kaiser Lukasz","year":"2017"},{"key":"e_1_3_2_1_70_1","first-page":"4","article-title":"Learning with Whom to Share in Multi-task Feature Learning","volume":"2","author":"Kang Zhuoliang","year":"2011","journal-title":"ICML"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275188"},{"key":"e_1_3_2_1_72_1","volume-title":"2017 Manila International Conference on\" Trends in Engineering and Technology\"(MTET-17)","author":"Kim Changhyung","year":"2017"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_30"},{"key":"e_1_3_2_1_75_1","unstructured":"Alex Krizhevsky Geoffrey Hinton etal 2009. Learning multiple layers of features from tiny images. Technical Report. Citeseer.  Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. Technical Report. Citeseer."},{"key":"e_1_3_2_1_76_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_77_1","volume-title":"Learning task grouping and overlap in multi-task learning. arXiv preprint arXiv:1206.6417","author":"Kumar Abhishek","year":"2012"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2017.2940968"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_80_1","unstructured":"Yann LeCun John S Denker and Sara A Solla. 1990. Optimal brain damage. In Advances in neural information processing systems. 598--605.  Yann LeCun John S Denker and Sara A Solla. 1990. Optimal brain damage. In Advances in neural information processing systems. 598--605."},{"key":"e_1_3_2_1_81_1","volume-title":"International conference on artificial neural networks","volume":"60","author":"LeCun Yann","year":"1995"},{"key":"e_1_3_2_1_82_1","volume-title":"International Conference on Machine Learning. 230--238","author":"Lee Giwoong","year":"2016"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360030"},{"key":"e_1_3_2_1_84_1","volume-title":"Theory of point estimation","author":"Lehmann Erich L"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"e_1_3_2_1_86_1","unstructured":"Hao Li Soham De Zheng Xu Christoph Studer Hanan Samet and Tom Goldstein. 2017. Training quantized nets: A deeper understanding. In Advances in Neural Information Processing Systems. 5811--5821.  Hao Li Soham De Zheng Xu Christoph Studer Hanan Samet and Tom Goldstein. 2017. Training quantized nets: A deeper understanding. In Advances in Neural Information Processing Systems. 5811--5821."},{"key":"e_1_3_2_1_87_1","volume-title":"Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710","author":"Li Hao","year":"2016"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.78"},{"key":"e_1_3_2_1_89_1","unstructured":"Xuejiao Li and Zixuan Zhou. [n.d.]. Speech Command Recognition with Convolutional Neural Network. ([n. d.]).  Xuejiao Li and Zixuan Zhou. [n.d.]. Speech Command Recognition with Convolutional Neural Network. ([n. d.])."},{"key":"e_1_3_2_1_90_1","volume-title":"Sep-nets: Small and effective pattern networks. arXiv preprint arXiv:1706.03912","author":"Li Zhe","year":"2017"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487381"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"e_1_3_2_1_94_1","volume-title":"Adversarial multi-task learning for text classification. arXiv preprint arXiv:1704.05742","author":"Liu Pengfei","year":"2017"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"e_1_3_2_1_96_1","unstructured":"Mingsheng Long Zhangjie Cao Jianmin Wang and S Yu Philip. 2017. Learning multiple tasks with multilinear relationship networks. In Advances in Neural Information Processing Systems. 1594--1603.  Mingsheng Long Zhangjie Cao Jianmin Wang and S Yu Philip. 2017. Learning multiple tasks with multilinear relationship networks. In Advances in Neural Information Processing Systems. 1594--1603."},{"key":"e_1_3_2_1_97_1","volume-title":"Zhe Zhao2 Jilin Chen2 Ang Li, and Lichan Hong","author":"Ma Jiaqi","year":"2019"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17010130"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_3_2_1_102_1","unstructured":"Andrew M McDonald Massimiliano Pontil and Dimitris Stamos. 2014. Spectral k-support norm regularization. In Advances in neural information processing systems. 3644--3652.  Andrew M McDonald Massimiliano Pontil and Dimitris Stamos. 2014. Spectral k-support norm regularization. In Advances in neural information processing systems. 3644--3652."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_104_1","volume-title":"SNN: stacked neural networks. arXiv preprint arXiv:1605.08512","author":"Mohammadi Milad","year":"2016"},{"key":"e_1_3_2_1_105_1","volume-title":"Multi-domain dialog state tracking using recurrent neural networks. arXiv preprint arXiv:1506.07190","author":"Mrk\u0161i\u0107 Nikola","year":"2015"},{"key":"e_1_3_2_1_106_1","volume-title":"K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning. arXiv preprint arXiv:1810.10703","author":"Mudrakarta Pramod Kaushik","year":"2018"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"e_1_3_2_1_108_1","unstructured":"Yuval Netzer Tao Wang Adam Coates Alessandro Bissacco Bo Wu and Andrew Y Ng. 2011. Reading digits in natural images with unsupervised feature learning. (2011).  Yuval Netzer Tao Wang Adam Coates Alessandro Bissacco Bo Wu and Andrew Y Ng. 2011. Reading digits in natural images with unsupervised feature learning. (2011)."},{"key":"e_1_3_2_1_109_1","volume-title":"Simplifying neural networks by soft weight-sharing. Neural computation 4, 4","author":"Nowlan Steven J","year":"1992"},{"key":"e_1_3_2_1_110_1","unstructured":"NVIDIA. 2019. Jetson Nano. https:\/\/developer.nvidia.com\/embedded\/jetson-nano-developer-kit.  NVIDIA. 2019. Jetson Nano. https:\/\/developer.nvidia.com\/embedded\/jetson-nano-developer-kit."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3122027"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"crossref","unstructured":"Hiroki Ota Minghan Chao Yuji Gao Eric Wu Li-Chia Tai Kevin Chen Yasutomo Matsuoka Kosuke Iwai Hossain M Fahad Wei Gao etal 2017. 3d printed \"earable\" smart devices for real-time detection of core body temperature. ACS sensors 2 7 (2017) 990--997.  Hiroki Ota Minghan Chao Yuji Gao Eric Wu Li-Chia Tai Kevin Chen Yasutomo Matsuoka Kosuke Iwai Hossain M Fahad Wei Gao et al. 2017. 3d printed \"earable\" smart devices for real-time detection of core body temperature. ACS sensors 2 7 (2017) 990--997.","DOI":"10.1021\/acssensors.7b00247"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_114_1","volume-title":"Christopher Kanan, and Stefan Wermter.","author":"Parisi German I","year":"2019"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00051-4"},{"key":"e_1_3_2_1_116_1","volume-title":"Holistic sparsecnn: Forging the trident of accuracy, speed, and size. arXiv preprint arXiv:1608.01409 1, 2","author":"Park Jongsoo","year":"2016"},{"key":"e_1_3_2_1_117_1","volume-title":"Revisiting natural gradient for deep networks. arXiv preprint arXiv:1301.3584","author":"Pascanu Razvan","year":"2013"},{"key":"e_1_3_2_1_118_1","unstructured":"Christian Plessl and Marco Platzner. 2004. Virtualization of Hardware-Introduction and Survey.. In ERSA. Citeseer 63--69.  Christian Plessl and Marco Platzner. 2004. Virtualization of Hardware-Introduction and Survey.. In ERSA. Citeseer 63--69."},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2494536"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_55"},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"e_1_3_2_1_123_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014"},{"key":"e_1_3_2_1_124_1","volume-title":"Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes","author":"Roth Wolfgang","year":"2018"},{"key":"e_1_3_2_1_125_1","volume-title":"An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098","author":"Ruder Sebastian","year":"2017"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"crossref","unstructured":"Tara Sainath and Carolina Parada. 2015. Convolutional neural networks for small-footprint keyword spotting. (2015).  Tara Sainath and Carolina Parada. 2015. Convolutional neural networks for small-footprint keyword spotting. (2015).","DOI":"10.21437\/Interspeech.2015-352"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2665671"},{"key":"e_1_3_2_1_131_1","volume-title":"Combinatorial optimization: polyhedra and efficiency","author":"Schrijver Alexander"},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00376-7"},{"key":"e_1_3_2_1_134_1","volume-title":"Operating system concepts","author":"Silberschatz Abraham"},{"key":"e_1_3_2_1_135_1","volume-title":"Peter Baer Galvin, and Greg Gagne","author":"Silberschatz Abraham","year":"2012"},{"key":"e_1_3_2_1_136_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_1_137_1","unstructured":"Vikas Sindhwani Tara Sainath and Sanjiv Kumar. 2015. Structured transforms for small-footprint deep learning. In Advances in Neural Information Processing Systems. 3088--3096.  Vikas Sindhwani Tara Sainath and Sanjiv Kumar. 2015. Structured transforms for small-footprint deep learning. In Advances in Neural Information Processing Systems. 3088--3096."},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_14"},{"key":"e_1_3_2_1_139_1","volume-title":"A survey of storage virtualization. Mini-micro Systems 4","author":"Song WU","year":"2003"},{"key":"e_1_3_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3155-2_1"},{"key":"e_1_3_2_1_141_1","first-page":"1693","article-title":"Classification of domestic robots","volume":"1","author":"Spyridon Mouroutsos G","year":"2012","journal-title":"Proceedings in ARSA-Advanced Research in Scientific Areas"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00030-1"},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690420913"},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19071733"},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_2_1_147_1","unstructured":"Cheng Tai Tong Xiao Yi Zhang Xiaogang Wang etal 2015. Convolutional neural networks with low-rank regularization. arXiv preprint arXiv:1511.06067 (2015).  Cheng Tai Tong Xiao Yi Zhang Xiaogang Wang et al. 2015. Convolutional neural networks with low-rank regularization. arXiv preprint arXiv:1511.06067 (2015)."},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18030733"},{"key":"e_1_3_2_1_149_1","unstructured":"TexasInstruments. 2018. MSP430FR5994. http:\/\/www.ti.com\/product\/MSP430FR5994.  TexasInstruments. 2018. MSP430FR5994. http:\/\/www.ti.com\/product\/MSP430FR5994."},{"key":"e_1_3_2_1_150_1","first-page":"489","article-title":"Discovering structure in multiple learning tasks: The TC algorithm","volume":"96","author":"Thrun Sebastian","year":"1996","journal-title":"ICML"},{"key":"e_1_3_2_1_151_1","volume-title":"Computer Hardware-Software Architecture","author":"Toy Wing N"},{"key":"e_1_3_2_1_152_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472157"},{"key":"e_1_3_2_1_153_1","volume-title":"Soft weight-sharing for neural network compression. arXiv preprint arXiv:1702.04008","author":"Ullrich Karen","year":"2017"},{"key":"e_1_3_2_1_154_1","unstructured":"Frank Uyeda. 2009. Lecture 7: Memory Management CSE 120: Principles of Operating Systems. http:\/\/cseweb.ucsd.edu\/classes\/su09\/cse120\/lectures\/Lecture7.pdf  Frank Uyeda. 2009. Lecture 7: Memory Management CSE 120: Principles of Operating Systems. http:\/\/cseweb.ucsd.edu\/classes\/su09\/cse120\/lectures\/Lecture7.pdf"},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_156_1","volume-title":"Places205-vggnet models for scene recognition. arXiv preprint arXiv:1508.01667","author":"Wang Limin","year":"2015"},{"key":"e_1_3_2_1_157_1","unstructured":"Yue Wang Tan Nguyen Yang Zhao Zhangyang Wang Yingyan Lin and Richard Baraniuk. 2018. EnergyNet: Energy-Efficient Dynamic Inference. (2018).  Yue Wang Tan Nguyen Yang Zhao Zhangyang Wang Yingyan Lin and Richard Baraniuk. 2018. EnergyNet: Energy-Efficient Dynamic Inference. (2018)."},{"key":"e_1_3_2_1_158_1","volume-title":"Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209","author":"Warden Pete","year":"2018"},{"key":"e_1_3_2_1_159_1","volume-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition. ArXiv e-prints (April","author":"Warden P.","year":"2018"},{"key":"e_1_3_2_1_160_1","unstructured":"Douglas Brent West etal 1996. Introduction to graph theory. Vol. 2. Prentice hall Upper Saddle River NJ.  Douglas Brent West et al. 1996. Introduction to graph theory. Vol. 2. Prentice hall Upper Saddle River NJ."},{"key":"e_1_3_2_1_161_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.88"},{"key":"e_1_3_2_1_162_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"e_1_3_2_1_163_1","volume-title":"Towards monocular vision based obstacle avoidance through deep reinforcement learning. arXiv preprint arXiv:1706.09829","author":"Xie Linhai","year":"2017"},{"key":"e_1_3_2_1_164_1","volume-title":"Deep multi-task representation learning: A tensor factorisation approach. arXiv preprint arXiv:1605.06391","author":"Yang Yongxin","year":"2016"},{"key":"e_1_3_2_1_165_1","volume-title":"Trace norm regularised deep multi-task learning. arXiv preprint arXiv:1606.04038","author":"Yang Yongxin","year":"2016"},{"key":"e_1_3_2_1_166_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"},{"key":"e_1_3_2_1_167_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2381131"},{"key":"e_1_3_2_1_168_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131675"},{"key":"e_1_3_2_1_169_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"e_1_3_2_1_170_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306093"},{"key":"e_1_3_2_1_171_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5050-1"},{"key":"e_1_3_2_1_172_1","volume-title":"Dynamically hierarchy revolution: dirnet for compressing recurrent neural network on mobile devices. arXiv preprint arXiv:1806.01248","author":"Zhang Jie","year":"2018"},{"key":"e_1_3_2_1_173_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2016.2573280"},{"key":"e_1_3_2_1_174_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx105"},{"key":"e_1_3_2_1_175_1","volume-title":"A survey on multi-task learning. arXiv preprint arXiv:1707.08114","author":"Zhang Yu","year":"2017"},{"key":"e_1_3_2_1_176_1","doi-asserted-by":"publisher","DOI":"10.5555\/2540128.2540403"},{"key":"e_1_3_2_1_177_1","volume-title":"Multilabel relationship learning. ACM Transactions on Knowledge Discovery from Data (TKDD) 7, 2","author":"Zhang Yu","year":"2013"},{"key":"e_1_3_2_1_178_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"e_1_3_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"e_1_3_2_1_180_1","volume-title":"Object detectors emerge in deep scene cnns. arXiv preprint arXiv:1412.6856","author":"Zhou Bolei","year":"2014"},{"key":"e_1_3_2_1_181_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_182_1","unstructured":"Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495.  Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495."},{"key":"e_1_3_2_1_183_1","volume-title":"Flexible clustered multi-task learning by learning representative tasks","author":"Zhou Qiang","year":"2015"}],"event":{"name":"MobiSys '20: The 18th Annual International Conference on Mobile Systems, Applications, and Services","location":"Toronto Ontario Canada","acronym":"MobiSys '20","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386901.3388947","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386901.3388947","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386901.3388947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:26Z","timestamp":1750199606000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386901.3388947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,15]]},"references-count":182,"alternative-id":["10.1145\/3386901.3388947","10.1145\/3386901"],"URL":"https:\/\/doi.org\/10.1145\/3386901.3388947","relation":{},"subject":[],"published":{"date-parts":[[2020,6,15]]},"assertion":[{"value":"2020-06-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}