{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:10:02Z","timestamp":1730297402577,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10393928","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"899-904","source":"Crossref","is-referenced-by-count":0,"title":["Training Knowledge Inheritance Through Deep Q-Net"],"prefix":"10.1109","author":[{"given":"Enzhi","family":"Zhang","sequence":"first","affiliation":[{"name":"Grad. School of Info. Science and Technology, Hokkaido University,Sapporo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruqin","family":"Wang","sequence":"additional","affiliation":[{"name":"Grad. School of Info. Science and Technology, Hokkaido University,Sapporo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science,Kobe,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhong","sequence":"additional","affiliation":[{"name":"Grad. School of Info. Science and Technology, Hokkaido University,Sapporo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaharu","family":"Munetomo","sequence":"additional","affiliation":[{"name":"Information Initiative Center, Hokkaido University,Sapporo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Horovod: fast and easy distributed deep learning in tensorflow","author":"Sergeev","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref9","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","volume":"31","author":"Garipov","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"12","key":"ref16","first-page":"6","article-title":"Scaling sgd batch size to 32k for imagenet training","volume":"6","author":"You","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref18","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"International conference on machine learning","author":"Pham","year":"2018"},{"key":"ref19","first-page":"5853","author":"Li","year":"2020","journal-title":"Neural architecture search in a proxy validation loss landscape"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref21","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"volume-title":"Cifar-10 (canadian institute for advanced research)","author":"Krizhevsky","key":"ref23"},{"volume-title":"Cifar-100 (canadian institute for advanced research)","author":"Krizhevsky","key":"ref24"},{"key":"ref25","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Glorot","year":"2010"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2023,10,1]]},"location":"Honolulu, Oahu, HI, USA","end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10393928.pdf?arnumber=10393928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:56:46Z","timestamp":1706792206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10393928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10393928","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}