{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T09:07:19Z","timestamp":1744276039558},"reference-count":20,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1587\/transinf.2022pap0003","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T22:18:32Z","timestamp":1669846712000},"page":"2048-2056","source":"Crossref","is-referenced-by-count":2,"title":["Multilayer Perceptron Training Accelerator Using Systolic Array"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Takeshi","family":"SENOO","sequence":"first","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"JINGUJI","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryosuke","family":"KURAMOCHI","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroki","family":"NAKAHARA","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] H. Liu, Z. Dai, D.R. So, and Q.V. Le, \u201cPay attention to MLPs,\u201d arXiv preprint arXiv:2105.08050, 2021. 10.48550\/arXiv.2105.08050"},{"key":"2","unstructured":"[2] O. Yadan, K. Adams, Y. Taigman, and M.A. Ranzato, \u201cMulti-gpu training of convnets,\u201d 2015. arXiv preprint arXiv:1312.5853. 10.48550\/arXiv.1312.5853"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] S. Cadambi, A. Majumdar, M. Becchi, S. Chakradhar, and H.P. Graf, \u201cA programmable parallel accelerator for learning and classification,\u201d 2010 19th Int. Conf. Parallel Architectures and Compilation Techniques, pp.273-283, Sept. 2010. 10.1145\/1854273.1854309","DOI":"10.1145\/1854273.1854309"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[5] R.G. Girones R.C. Palero, J.C. Boluda, and A.S. Cortes\u201cFPGA implementation of a pipelined on-line backpropagation,\u201d J. VLSI signal processing systems for signal, image and video technology, vol.40, no.2, pp.189-213, 2005. 10.1007\/s11265-005-4961-3","DOI":"10.1007\/s11265-005-4961-3"},{"key":"5","unstructured":"[6] W. Zhao, H. Fu, W. Luk, T. Yu, S. Wang, B. Feng, Y. Ma, and G. Yang, \u201cF-CNN: An FPGA-based framework for training Convolutional Neural Networks,\u201d IEEE 27th Int. Conf. Application-specific Systems, Architectures and Processors (ASAP), 2016. 10.1109\/ASAP.2016.7760779"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[7] T. Geng, T. Wang, A. Sanaullah, C. Yang, R. Xu, R. Patel, and M.C. Herbordt, \u201cFPDeep: Acceleration and load balancing of CNN training on FPGA clusters,\u201d FCCM, pp.81-84, 2018. 10.1109\/FCCM.2018.00021","DOI":"10.1109\/FCCM.2018.00021"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[8] M. Isakov, A. Ehret, and M.A. Kinsy, \u201cClosNets: Batchless DNN training with on-chip a priori sparse neural topologies,\u201d FPL, pp.55-59, 2018. 10.1109\/FPL.2018.00017","DOI":"10.1109\/FPL.2018.00017"},{"key":"8","unstructured":"[9] Z. Huo, B. Gu, Q. Yang, and H. Huang, \u201cDecoupled parallel backpropagation with convergence guarantee,\u201d ICML, pp.2103-2111, 2018. 10.48550\/arXiv.1804.10574"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[10] T. Senoo, A. Jinguji, R. Kuramochi, and H. Nakahara, \u201cA multilayer perceptron training accelerator using systolic array,\u201d APCCAS, pp.173-176, 2021. 10.1109\/APCCAS51387.2021.9687773","DOI":"10.1109\/APCCAS51387.2021.9687773"},{"key":"10","unstructured":"[11] X. Glorot and Y. Bengio, \u201cUnderstanding the difficulty of training deep feedforward neural networks,\u201d J. Mach. Learn. Res., vol.9, pp.249-256, 2010."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[12] H. Nakahara, H. Yonekawa, and S. Sato, \u201cAn object detector based on multiscale sliding window search using a fully pipelined binarized CNN on an FPGA,\u201d ICFPT, pp.168-175, 2017. 10.1109\/FPT.2017.8280135","DOI":"10.1109\/FPT.2017.8280135"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[13] N. Moustafa and J. Slay, \u201cUNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set),\u201d 2015 Military Communications and Information Systems Conference (MilCIS), pp.1-6, 2015 10.1109\/MilCIS.2015.7348942","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[14] S. Cadambi, A. Majumdar, M. Becchi, S. Chakradhar, and H.P. Graf, \u201cA programmable parallel accelerator for learning and classification,\u201d Proc. 19th Int. Conf. Parallel architectures and compilation techniques, pp.273-284, Sept. 2012. 10.1145\/1854273.1854309","DOI":"10.1145\/1854273.1854309"},{"key":"14","unstructured":"[15] M. Jaderberg, W.M. Czarnecki, S. Osindero, O. Vinyals, A. Graves, D. Silver, and K. Kavukcuoglu, \u201cDecoupled neural interfaces using synthetic gradients,\u201d arXiv preprint arXiv:1608.05343, 2016. 10.48550\/arXiv.1608.05343"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[16] Y. Umuroglu, Y. Akhauri, N.J. Fraser, and M. Blott, \u201cLogicNets: Co-designed neural networks and circuits for extreme-throughput applications, FPL, pp.291-297, 2020. 10.1109\/FPL50879.2020.00055","DOI":"10.1109\/FPL50879.2020.00055"},{"key":"16","unstructured":"[17] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, \u201cLearning representations by back-propagating errors,\u201d Cognitive modeling, vol.3, no.5, p.1, 1988. 10.1038\/323533a0"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[18] H. Robbins and S. Monro, \u201cA stochastic approximation method,\u201d The annals of mathematical statistics, pp.400-407, Sept. 1951. 10.1214\/aoms\/1177729586","DOI":"10.1214\/aoms\/1177729586"},{"key":"18","unstructured":"[19] M. Carreira-Perpinan and W. Wang, \u201cDistributed optimization of deeply nested systems,\u201d Proc. 17th Int. Conf. Artificial Intelligence and Statistics, pp.10-19, 2014."},{"key":"19","unstructured":"[20] W.M. Czarnecki, G. Swirszcz, M. Jaderberg, S. Osindero, O. Vinyals, and K. Kavukcuoglu, \u201cUnderstanding synthetic gradients and decoupled neural interfaces,\u201d arXiv preprint arXiv:1703.00522, 2017. 10.48550\/arXiv.1703.00522"},{"key":"20","unstructured":"[21] G. Taylor, R. Burmeister, Z. Xu, B. Singh, A. Patel, and T. Goldstein, \u201cTraining neural networks without gradients: A scalable admm approach,\u201d Int. Conf. Mach. Learn., pp.2722-2731, 2016. 10.48550\/arXiv.1605.02026"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/12\/E105.D_2022PAP0003\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T19:31:41Z","timestamp":1728502301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/12\/E105.D_2022PAP0003\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":20,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022pap0003","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2022,12,1]]},"article-number":"2022PAP0003"}}