{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T19:39:36Z","timestamp":1758397176199,"version":"3.44.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1109\/aspdac.2018.8297378","type":"proceedings-article","created":{"date-parts":[[2018,2,22]],"date-time":"2018-02-22T17:02:02Z","timestamp":1519318922000},"page":"534-539","source":"Crossref","is-referenced-by-count":13,"title":["Running sparse and low-precision neural network: When algorithm meets hardware"],"prefix":"10.1109","author":[{"given":"Bing","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Wei","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Jiachen","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Sicheng","family":"Li","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Palo Alto, CA, USA"}]},{"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]}],"member":"263","reference":[{"journal-title":"Tensorfiow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref31"},{"journal-title":"DoReFa-Net Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","year":"2016","author":"zhou","key":"ref30"},{"key":"ref10","first-page":"1379","article-title":"Dynamic network surgery for efficient dnns","author":"guo","year":"2016","journal-title":"NIPS"},{"key":"ref11","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203852"},{"key":"ref13","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"NIPS"},{"key":"ref14","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"2014","journal-title":"NIPS"},{"journal-title":"Speeding up convolutional neural networks with low rank expansions","year":"2014","author":"jaderberg","key":"ref15"},{"journal-title":"Training cnns with low-rank filters for efficient image classification","year":"2015","author":"ioannou","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.78"},{"key":"ref18","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178146"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967280"},{"journal-title":"Training deep neural networks with low precision multiplications","year":"2014","author":"courbariaux","key":"ref3"},{"key":"ref6","first-page":"1185","article-title":"Sparse feature learning for deep belief networks","author":"boureau","year":"2008","journal-title":"NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref5","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding","year":"2015","author":"han","key":"ref8"},{"key":"ref7","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90469-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref20","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"NIPS"},{"key":"ref22","article-title":"l-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns","author":"seide","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"journal-title":"Terngrad Ternary gradients to reduce communication in distributed deep learning","year":"2017","author":"wen","key":"ref24"},{"key":"ref23","article-title":"QSGD: randomized quantization for communication-optimal stochastic gradient descent","author":"alistarh","year":"2016","journal-title":"CoRR abs\/1610 02132"},{"journal-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","year":"2015","author":"kim","key":"ref26"},{"journal-title":"Convolutional neural networks with low-rank regularization","year":"2015","author":"tai","key":"ref25"}],"event":{"name":"2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC)","start":{"date-parts":[[2018,1,22]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2018,1,25]]}},"container-title":["2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8291862\/8297256\/08297378.pdf?arnumber=8297378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:23:10Z","timestamp":1756153390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8297378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/aspdac.2018.8297378","relation":{},"subject":[],"published":{"date-parts":[[2018,1]]}}}