{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:01:08Z","timestamp":1790683268538,"version":"4.1.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.K. EPSRC","award":["EP\/L016796\/1"],"award-info":[{"award-number":["EP\/L016796\/1"]}]},{"name":"U.K. EPSRC","award":["EP\/N031768\/1"],"award-info":[{"award-number":["EP\/N031768\/1"]}]},{"name":"U.K. EPSRC","award":["EP\/P010040\/1"],"award-info":[{"award-number":["EP\/P010040\/1"]}]},{"name":"U.K. EPSRC","award":["EP\/V028251\/1"],"award-info":[{"award-number":["EP\/V028251\/1"]}]},{"name":"U.K. EPSRC","award":["EP\/S030069\/1"],"award-info":[{"award-number":["EP\/S030069\/1"]}]},{"name":"Corerain"},{"name":"Maxeler"},{"name":"Intel","award":["Xilinx"],"award-info":[{"award-number":["Xilinx"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpds.2022.3153682","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T20:28:36Z","timestamp":1645648116000},"page":"3387-3399","source":"Crossref","is-referenced-by-count":13,"title":["Accelerating Bayesian Neural Networks via Algorithmic and Hardware Optimizations"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2387-5611","authenticated-orcid":false,"given":"Hongxiang","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4031-6398","authenticated-orcid":false,"given":"Martin","family":"Ferianc","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9263-6529","authenticated-orcid":false,"given":"Zhiqiang","family":"Que","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Niu","sequence":"additional","affiliation":[{"name":"Corerain Technologies Ltd., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8908-847X","authenticated-orcid":false,"given":"Miguel","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref38","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055240"},{"key":"ref32","article-title":"On calibration of modern neural networks","author":"guo","year":"2017"},{"key":"ref31","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011"},{"key":"ref30","article-title":"The MNIST database of handwritten digits","author":"lecun","year":"1998"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref36","first-page":"929","article-title":"On the effects of quantisation on model uncertainty in bayesian neural networks","author":"ferianc","year":"2021","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref34","article-title":"On efficient uncertainty estimation for resource-constrained mobile applications","author":"rock","year":"2021"},{"key":"ref28","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015"},{"key":"ref27","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","article-title":"Being Bayesian, even just a bit, fixes overconfidence in ReLU networks","author":"kristiadi","year":"2020"},{"key":"ref2","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","article-title":"Stochastic-YOLO: Efficient probabilistic object detection under dataset shifts","author":"azevedo","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14541"},{"key":"ref11","article-title":"Bayesian LSTMs in medicine","author":"van der westhuizen","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586137"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00030"},{"key":"ref13","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref16","article-title":"Confidence calibration for convolutional neural networks using structured dropout","author":"zhang","year":"2019"},{"key":"ref17","article-title":"Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding","author":"kendall","year":"2015"},{"key":"ref18","article-title":"Understanding deep neural networks with rectified linear units","author":"arora","year":"2016"},{"key":"ref19","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015"},{"key":"ref4","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569814"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/computers10060082"},{"key":"ref8","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-020-00390-8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286149"},{"key":"ref9","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref46","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","author":"hoefler","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173212"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116302"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375312"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9790018\/09720069.pdf?arnumber=9720069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:29:39Z","timestamp":1656361779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9720069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":49,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3153682","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}