{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:50:32Z","timestamp":1725947432671},"reference-count":21,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1587\/transinf.2022pap0001","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T22:18:31Z","timestamp":1669846711000},"page":"2040-2047","source":"Crossref","is-referenced-by-count":1,"title":["Holmes: A Hardware-Oriented Optimizer Using Logarithms"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Yoshiharu","family":"YAMAGISHI","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, Hokkaido University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"KANEKO","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, Hokkaido University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Megumi","family":"AKAI-KASAYA","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Hokkaido, Hokkaido University"},{"name":"Graduate School of Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"ASAI","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Hokkaido, Hokkaido University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] T. Kaneko, K. Orimo, I. Hida, S. Takamaeda-Yamazaki, M. Ikebe, M. Motomura, and T. Asai, \u201cA study on a low power optimization algorithm for an edge-AI device,\u201d NOLTA, vol.10, no.4, pp.373-389, 2019. 10.1587\/nolta.10.373","DOI":"10.1587\/nolta.10.373"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] R. Bez and A. Pirovano. \u201cNon-volatile memory technologies: emerging concepts and new materials,\u201d Materials Science in Semiconductor Processing, vol.7, no.4-6, pp.349-355, 2004. 10.1016\/j.mssp.2004.09.127","DOI":"10.1016\/j.mssp.2004.09.127"},{"key":"3","unstructured":"[3] K. Guo, S. Zeng, J. Yu, Y. Wang, and H. Yang, \u201cA survey of FPGA based neural network accelerator,\u201d arXiv preprint, arXiv:1712.08934, 2017."},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] A. Ankit, I.E. Hajj, S.R. Chalamalasetti, G. Ndu, M. Foltin, R.S. Williams, P. Faraboschi, W.-M.W. Hwu, J.P. Strachan, K. Roy, and D.S. Milojicic, \u201cPUMA: A programmable ultra-efficient memristor-based accelerator for machine learning inference,\u201d In: ASPLOS &apos;19: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, April, pp.715-731, 2019. 10.1145\/3297858.3304049","DOI":"10.1145\/3297858.3304049"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] J. Lee, J. Lee, D. Han, J. Lee, G. Park, and H.-J. Yoo, \u201cLNPU: A 25.3TFLOPS\/W sparse deep-neural-network learning processor with fine-grained mixed precision of FP8-FP16,\u201d In: 2019 IEEE International Solid-State Circuits Conference (ISSCC) Session 7.7, pp.142-144, 2019. 10.1109\/isscc.2019.8662302","DOI":"10.1109\/ISSCC.2019.8662302"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] B. Fleischer, S. Shukla, M. Ziegler, J. Silberman, J. Oh, V. Srinivasan, J. Choi, S. Mueller, A. Agrawal, T. Babinsky, N. Cao, C.-Y. Chen, P. Chuang, T. Fox, G. Gristede, M. Guillorn, H. Haynie, M. Klaiber, D. Lee, S.-H. Lo, G. Maier, M. Scheuermann, S. Venkataramani, C. Vezyrtzis, N. Wang, F. Yee, C. Zhou, P.-F. Lu, B. Curran, L. Chang, and K. Gopalakrishnan, \u201cA scalable Multi-TeraOPS deep learning processor core for AI training and inference,\u201d In: 2018 Symposium on VLSI Circuits Digest of Technical Papers C4-2, pp.C35-C36, 2018. 10.1109\/vlsic.2018.8502276","DOI":"10.1109\/VLSIC.2018.8502276"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] D. Han, J. Lee, J. Lee, and H.-J. Yoo, \u201cA 1.32 TOPS\/W energy efficient deep neural network learning processor with direct feedback alignment based heterogeneous core architecture,\u201d In: 2019 Symposium on VLSI Circuits Digest of Technical Papers C24-3, pp.C304-C305, 2019. 10.23919\/vlsic.2019.8778006","DOI":"10.23919\/VLSIC.2019.8778006"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] C. Kim, S. Kang, D. Shin, S. Choi, Y. Kim, and H.-J. Yoo, \u201cA 2.1TFLOPS\/W mobile deep RL accelerator with transposable PE array and experience compression,\u201d In: 2019 IEEE International Solid-State Circuits Conference (ISSCC), session 7.4, pp.136-138, 2019. 10.1109\/isscc.2019.8662447","DOI":"10.1109\/ISSCC.2019.8662447"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] T. Kaneko, H. Momose and T. Asai, \u201cAn FPGA accelerator for embedded microcontrollers implementing a ternarized backpropagation algorithm,\u201d In: 2019 International Conference on ReConFigurable Computing and FPGAs (ReConFig), pp.1-8, 2019. 10.1109\/reconfig48160.2019.8994795","DOI":"10.1109\/ReConFig48160.2019.8994795"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] K. Wakabayashi, \u201cUse of high-level synthesis to generate hardware from software-Another alternative general-purpose program-executing mechanism to the CPU,\u201d IEICE, vol.6, no.1, pp.37-50, July 2012.","DOI":"10.1587\/essfr.6.37"},{"key":"11","unstructured":"[11] D. Choi, C.J. Shallue, Z. Nado, et al., \u201cOn empirical comparisons of optimizers for deep learning,\u201d ICLR 2020 Conference Blind Submission, June 2020."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] L. Bottou, \u201cLarge-scale machine learning with stochastic gradient descent,\u201d COMPSTAT&apos;10, pp.177-186, Aug. 2010.","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] B.T. Polyak, \u201cSome methods of speeding up the convergence of iteration methods,\u201d USSR Computational Mathematics and Mathematical Physics, vol.4, no.5, pp.1-17, 1964. 10.1016\/0041-5553(64)90137-5","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] N. Qian, \u201cOn the momentum term in gradient descent learning algorithms,\u201d Neural Networks, vol.12, no.1, pp.145-151, 1999. 10.1016\/s0893-6080(98)00116-6","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"15","unstructured":"[15] T. Tieleman and G. Hinton, Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude, COURSERA: Neural Networks for Machine Learning, 2012."},{"key":"16","unstructured":"[16] Y. Nesterov, \u201cA method for solving the convex programming problem with convergence rate O(1\/<i>k<\/i><sup>2<\/sup>),\u201d Doklady AN USSR, vol.269, pp.543-547, 1983."},{"key":"17","unstructured":"[17] J. Duchi, E. Hazan, and Y. Singer, \u201cAdaptive subgradient methods for online learning and stochastic optimization,\u201d Journal of Machine Learning Research, vol.12, pp.2121-2159, 2011."},{"key":"18","unstructured":"[18] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d In: The International Conference on Learning Representations (ICLR), 2015."},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] H. Mitome, P.M. Yan, and R. Ishii, \u201cHardware Design of Dividers and It&apos;s Evaluation,\u201d The Institute of Electrical Engineers of Japan, C, A publication of Electronics, Information and Systems Society, vol.116, no.5, pp.534-539, 1996. 10.1541\/ieejeiss1987.116.5_534","DOI":"10.1541\/ieejeiss1987.116.5_534"},{"key":"20","unstructured":"[20] B. Neyshabur, R. Tomioka, and N. Srebro, \u201cIn search of the real inductive bias: On the role of implicit regularization in deep learning,\u201d In: International Conference on Learning Representations (ICLR), 2015."},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] R. Bez, E. Camerlenghi, A. Modelli, and A. Visconti, \u201cIntroduction to flash memory,\u201d IEEE, vol.91, no.4, pp.489-502, April 2003. 10.1109\/jproc.2003.811702","DOI":"10.1109\/JPROC.2003.811702"}],"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_2022PAP0001\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T04:54:58Z","timestamp":1715316898000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/12\/E105.D_2022PAP0001\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":21,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022pap0001","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]},"article-number":"2022PAP0001"}}