{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:32:47Z","timestamp":1759332767832,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant"},{"DOI":"10.13039\/501100003708","name":"Korean Government through Ministry of Science and ICT (MSIT)","doi-asserted-by":"publisher","award":["2019-0-00533"],"award-info":[{"award-number":["2019-0-00533"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government through MSIT","award":["NRF-2022R1A2C1011469"],"award-info":[{"award-number":["NRF-2022R1A2C1011469"]}]},{"DOI":"10.13039\/100004358","name":"Samsung Electronics Company Ltd","doi-asserted-by":"publisher","award":["IO210204-08384-01"],"award-info":[{"award-number":["IO210204-08384-01"]}],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3166158","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T20:38:51Z","timestamp":1649709531000},"page":"38555-38564","source":"Crossref","is-referenced-by-count":4,"title":["Continual Learning With Speculative Backpropagation and Activation History"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-2176","authenticated-orcid":false,"given":"Sangwoo","family":"Park","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6377-5482","authenticated-orcid":false,"given":"Taeweon","family":"Suh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30102-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00076-5"},{"volume-title":"Top 20 Applications of Deep Learning in 2021 Across Industries","year":"2019","author":"Chatterjee","key":"ref3"},{"volume-title":"Tesla\u2019s Deep Learning at Scale: Using Billions of Miles to Train Neural Networks","year":"2019","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.97.2.285"},{"key":"ref7","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref10","article-title":"Gradient episodic memory for continual learning","author":"Lopez-Paz","year":"2017","journal-title":"arXiv:1706.08840"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref12","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Serra"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref14","article-title":"Variational continual learning","author":"Nguyen","year":"2017","journal-title":"arXiv:1710.10628"},{"key":"ref15","first-page":"3762","article-title":"Orthogonal gradient descent for continual learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Farajtabar"},{"issue":"13","key":"ref16","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"James","year":"2017","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref17","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"issue":"3","key":"ref20","first-page":"367","article-title":"Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks","volume":"44","author":"Chen","year":"2016","journal-title":"IEEE Micro"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"volume-title":"EdgeTPU","year":"2019","key":"ref22"},{"volume-title":"Cornami Achieves Unprecedented Performance at Lowest Power Dissipation for Deep Neural Networks","year":"2019","key":"ref23"},{"article-title":"Tearing apart Google\u2019s TPU 3.0 AI coprocessor","year":"2018","author":"Teich","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2975185"},{"article-title":"Habana offers Gaudi for AI training","year":"2019","author":"Gwennap","key":"ref26"},{"volume-title":"Baidu Accelerator Rises in AI","year":"2018","author":"Merritt","key":"ref27"},{"volume-title":"Baidu Creates Kunlun Silicon for AI","year":"2018","author":"Duckett","key":"ref28"},{"volume-title":"The 2,048-Core PEZY-SC2 Sets a Green500 Record\u2014WikiChip Fuse","year":"2017","author":"Schor","key":"ref29"},{"article-title":"Tenstorrent scales AI performance: Architecture leads in data-center power efficiency","year":"2020","author":"Gwennap","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286149"},{"volume-title":"Cornami Achieves Unprecedented Performance at Lowest Power Dissipation for Deep Neural Networks","year":"2019","key":"ref32"},{"article-title":"Performance estimation and benchmarks for real-world edge inference applications","volume-title":"Proc. Linley Spring Processor Conf","author":"Mehta","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00059"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM51124.2021.00046"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3040849"},{"volume-title":"MNIST Handwritten Digit Database","year":"2020","author":"LeCun","key":"ref37"},{"key":"ref38","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref39","article-title":"Overcoming catastrophic forgetting by incremental moment matching","author":"Lee","year":"2017","journal-title":"arXiv:1703.08475"},{"key":"ref40","article-title":"Online structured Laplace approximations for overcoming catastrophic forgetting","author":"Ritter","year":"2018","journal-title":"arXiv:1805.07810"},{"key":"ref41","article-title":"Continual learning with deep generative replay","author":"Shin","year":"2017","journal-title":"arXiv:1705.08690"},{"key":"ref42","article-title":"Towards robust evaluations of continual learning","author":"Farquhar","year":"2018","journal-title":"arXiv:1805.09733"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref44","first-page":"4","article-title":"SDSoC: A higher-level programming environment for Zynq SoC and ultrascale+ MPSoC","volume-title":"Proc. ACM\/SIGDA Int. Symp. Field-Program. Gate Arrays","author":"Kathail"},{"key":"ref45","article-title":"Re-evaluating continual learning scenarios: A categorization and case for strong baselines","author":"Hsu","year":"2018","journal-title":"arXiv:1810.12488"},{"volume-title":"Zynq UltraScale+ MPSoC ZCU102 Evaluation Kit","year":"2021","key":"ref46"},{"volume-title":"Zynq UltraScale+ MPSoC","year":"2021","key":"ref47"},{"volume-title":"Training Deep Net on 14 Million Images by Using a Single Machine","year":"2022","key":"ref48"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09754561.pdf?arnumber=9754561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:24:58Z","timestamp":1705688698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9754561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3166158","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}