{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:19:52Z","timestamp":1750220392899,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L016796\/1, EP\/N031768\/1, EP\/P010040\/1, EP\/V028251\/1 and EP\/S030069\/1"],"award-info":[{"award-number":["EP\/L016796\/1, EP\/N031768\/1, EP\/P010040\/1, EP\/V028251\/1 and EP\/S030069\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,10]]},"DOI":"10.1145\/3489517.3530451","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T23:19:29Z","timestamp":1661296769000},"page":"325-330","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Enabling fast uncertainty estimation"],"prefix":"10.1145","author":[{"given":"Hongxiang","family":"Fan","sequence":"first","affiliation":[{"name":"Imperial College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Ferianc","sequence":"additional","affiliation":[{"name":"University College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[{"name":"Imperial College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1402--1407","author":"Awano H.","key":"e_1_3_2_1_1_1","unstructured":"H. Awano and M. Hashimoto. 2020. BYNQNet: Bayesian Neural Network with Quadratic Activations for Sampling-Free Uncertainty Estimation on FPGA. In 2020 Design, Automation Test in Europe Conference Exhibition (DATE). 1402--1407."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)","volume":"53","author":"Ruizhe","unstructured":"Ruizhe Cai et al. 2018. VIBNN: Hardware acceleration of Bayesian neural networks. In Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), Vol. 53. 476--488."},{"key":"e_1_3_2_1_3_1","volume-title":"Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555","author":"Kevin Clark","year":"2020","unstructured":"Kevin Clark et al. 2020. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. CoRR","author":"Jacob Devlin","year":"2018","unstructured":"Jacob Devlin et al. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. CoRR (2018)."},{"volume-title":"International Conference on Field-Programmable Technology (ICFPT). IEEE, 28--35","author":"Hongxiang","key":"e_1_3_2_1_5_1","unstructured":"Hongxiang Fan et al. 2019. Static block floating-point quantization for convolutional neural networks on fpga. In International Conference on Field-Programmable Technology (ICFPT). IEEE, 28--35."},{"volume-title":"Proceedings of the 2021 ACM\/IEEE Design Automation Conference (DAC). IEEE, 1--6.","author":"Hongxiang","key":"e_1_3_2_1_6_1","unstructured":"Hongxiang Fan et al. 2021. High-Performance FPGA-based Accelerator for Bayesian Neural Networks. In Proceedings of the 2021 ACM\/IEEE Design Automation Conference (DAC). IEEE, 1--6."},{"volume-title":"ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). IEEE, 1--14","author":"Jeremy","key":"e_1_3_2_1_7_1","unstructured":"Jeremy Fowers et al. 2018. A configurable cloud-scale DNN processor for real-time AI. In ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). IEEE, 1--14."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning (ICML). 1050--1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning (ICML). 1050--1059."},{"volume-title":"IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 328--341","author":"Jun Tae","key":"e_1_3_2_1_9_1","unstructured":"Tae Jun Ham et al. 2020. A^ 3: Accelerating Attention Mechanisms in Neural Networks with Approximation. In IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 328--341."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Ranganath","unstructured":"Ranganath Krishnan et al. 2020. Specifying weight priors in bayesian deep neural networks with empirical bayes. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 4477--4484."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Leveraging uncertainty information from deep neural networks for disease detection","volume":"7","author":"Christian Leibig","year":"2017","unstructured":"Christian Leibig et al. 2017. Leveraging uncertainty information from deep neural networks for disease detection. Scientific Reports 7, 1 (2017), 1--14.","journal-title":"Scientific Reports"},{"volume-title":"ACM\/IEEE International Symposium on Low Power Electronics and Design (ISLPED). 175--180","author":"Bingbing","key":"e_1_3_2_1_12_1","unstructured":"Bingbing Li et al. 2020. FTRANS: energy-efficient acceleration of transformers using FPGA. In ACM\/IEEE International Symposium on Low Power Electronics and Design (ISLPED). 175--180."},{"key":"e_1_3_2_1_13_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Yinhan Liu","year":"2019","unstructured":"Yinhan Liu et al. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_14_1","unstructured":"Siyuan Lu et al. 2020. Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer. arXiv preprint arXiv:2009.08605 (2020)."},{"volume-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI),. 4745--4753","author":"Rowan","key":"e_1_3_2_1_15_1","unstructured":"Rowan McAllister et al. 2017. Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI),. 4745--4753."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 2019 Advances in neural information processing systems (NeurIPS) 32","author":"Adam","year":"2019","unstructured":"Adam Paszke et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Proceedings of the 2019 Advances in neural information processing systems (NeurIPS) 32 (2019), 8026--8037."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"e_1_3_2_1_18_1","unstructured":"Alec Radford et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_19_1","unstructured":"Colin Raffel et al. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications. arXiv preprint arXiv:2111.09838","author":"Rock Johanna","year":"2021","unstructured":"Johanna Rock, Tiago Azevedo, Ren\u00e9 de Jong, Daniel Ruiz-Mu\u00f1oz, and Partha Maji. 2021. On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications. arXiv preprint arXiv:2111.09838 (2021)."},{"key":"e_1_3_2_1_21_1","unstructured":"Victor Sanh et al. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. CoRR (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main","volume":"1840","author":"Artem","unstructured":"Artem Shelmanov et al. 2021. How Certain is Your Transformer?. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (EACL). 1833--1840."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Zhourui","unstructured":"Zhourui Song et al. 2018. Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32."},{"key":"e_1_3_2_1_24_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Nitish Srivastava","year":"2014","unstructured":"Nitish Srivastava et al. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 1929--1958.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_1_25_1","unstructured":"Evgenii Tsymbalov et al. 2020. Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling. arXiv preprint arXiv:2003.03274 (2020)."},{"key":"e_1_3_2_1_26_1","unstructured":"Ashish Vaswani et al. 2017. Attention is all you need. In Advances in neural information processing systems (NeurIPS). 5998--6008."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00030"},{"key":"e_1_3_2_1_28_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Alex Wang","year":"2018","unstructured":"Alex Wang et al. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning. IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Hanrui","year":"2021","unstructured":"Hanrui Wang et al. 2021. SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning. IEEE International Symposium on High Performance Computer Architecture (HPCA) (2021)."},{"key":"e_1_3_2_1_30_1","unstructured":"Thomas Wolf et al. 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)."},{"key":"e_1_3_2_1_31_1","unstructured":"Bichen Wu et al. 2020. Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)."},{"volume-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7378--7382","author":"Boyang","key":"e_1_3_2_1_32_1","unstructured":"Boyang Xue et al. 2021. Bayesian transformer language models for speech recognition. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7378--7382."},{"key":"e_1_3_2_1_33_1","volume-title":"Confidence calibration for convolutional neural networks using structured dropout. arXiv preprint arXiv:1906.09551","author":"Zhang Zhilu","year":"2019","unstructured":"Zhilu Zhang, Adrian V Dalca, and Mert R Sabuncu. 2019. Confidence calibration for convolutional neural networks using structured dropout. arXiv preprint arXiv:1906.09551 (2019)."},{"key":"e_1_3_2_1_34_1","unstructured":"Wangchunshu Zhou et al. 2020. Scheduled drophead: A regularization method for transformer models. arXiv preprint arXiv:2004.13342 (2020)."}],"event":{"name":"DAC '22: 59th ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"],"location":"San Francisco California","acronym":"DAC '22"},"container-title":["Proceedings of the 59th ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530451","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:39Z","timestamp":1750191519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530451"}},"subtitle":["accelerating bayesian transformers via algorithmic and hardware optimizations"],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":34,"alternative-id":["10.1145\/3489517.3530451","10.1145\/3489517"],"URL":"https:\/\/doi.org\/10.1145\/3489517.3530451","relation":{},"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}