{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:31:18Z","timestamp":1773246678225,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"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":[[2023,7,9]]},"DOI":"10.1109\/dac56929.2023.10247954","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:31Z","timestamp":1694799091000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA"],"prefix":"10.1109","author":[{"given":"Hongxiang","family":"Fan","sequence":"first","affiliation":[{"name":"Samsung AI Center & University of Cambridge,Cambridge,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Chen","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liam","family":"Castelli","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Que","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University,Department of Electronics and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth","family":"Long","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Physics,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"181","article-title":"Early exit ensembles for uncertainty quantification","volume":"158","author":"qendro","year":"2021","journal-title":"Proceedings of Machine Learning for Health"},{"key":"ref14","article-title":"Deep ensembles: A loss landscape perspective","author":"fort","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref10","article-title":"hls4ml: An open-source codesign workflow to empower scientific low-power machine learning devices","author":"fahim","year":"2021"},{"key":"ref2","first-page":"475","article-title":"Bayesian learning via stochastic dynamics","author":"neal","year":"1993","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"ref17","article-title":"Students are the best teacher: Exit-ensemble distillation with multi-exits","author":"lee","year":"2021"},{"key":"ref16","article-title":"Multi-scale dense networks for resource efficient image classification","author":"huang","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480120"},{"key":"ref18","first-page":"3301","article-title":"Shallow-deep networks: Understanding and mitigating network overthinking","volume":"97","author":"kaya","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref24","article-title":"Bayesian Segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding","author":"kendall","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3153682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586137"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3469261.3469404"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116302"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3160948"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SAMOS.2016.7818341"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2785257"},{"key":"ref4","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","first-page":"1613","article-title":"Weight uncertainty in neural network","author":"blundell","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref5","article-title":"Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift","volume":"32","author":"ovadia","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"2023 60th ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,7,9]]},"end":{"date-parts":[[2023,7,13]]}},"container-title":["2023 60th ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10247654\/10247655\/10247954.pdf?arnumber=10247954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:41:04Z","timestamp":1696268464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10247954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,9]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dac56929.2023.10247954","relation":{},"subject":[],"published":{"date-parts":[[2023,7,9]]}}}