{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:27:12Z","timestamp":1740101232836,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005946","name":"Hokkaido University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005946","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,29]]},"DOI":"10.1109\/scisisis55246.2022.10002143","type":"proceedings-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T18:38:52Z","timestamp":1672857532000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Learning from the Past: Regularization by Validation"],"prefix":"10.1109","author":[{"given":"Enzhi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hokkaido University,Grad. School of Info. Science and Technology,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":"Masaharu","family":"Munetomo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Information Initiative Center,Sapporo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016","journal-title":"arXiv preprint arXiv:1609.04836"},{"key":"ref3","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":"ref4","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018","journal-title":"arXiv preprint arXiv:1803.05407"},{"key":"ref5","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv preprint arXiv:1706.02677"},{"key":"ref6","first-page":"1437","article-title":"Bohb: Robust and efficient hyperparameter optimization at scale","volume-title":"International Conference on Machine Learning","author":"Falkner"},{"key":"ref7","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016","journal-title":"arXiv preprint arXiv:1611.01578"},{"key":"ref8","first-page":"5853","article-title":"Neural architecture search in a proxy validation loss landscape","author":"Li","year":"2020"},{"key":"ref9","article-title":"Comparing biases for minimal network construction with back-propagation","volume":"1","author":"Hanson","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume":"2","author":"Morgan","year":"1989","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref11","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref12","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv preprint arXiv:1412.6572"},{"key":"ref13","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv preprint arXiv:1706.06083"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref15","article-title":"Adversarial training can hurt generalization","author":"Raghunathan","year":"2019","journal-title":"arXiv preprint arXiv:1906.06032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref17","article-title":"Do we need zero training loss after achieving zero training error?","author":"Ishida","year":"2020","journal-title":"arXiv preprint arXiv:2002.08709"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"7","key":"ref20","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"Hinton","year":"2015","journal-title":"arXiv preprint arXiv:1503.02531"},{"key":"ref21","article-title":"Do deep convolutional nets really need to be deep and convolutional?","author":"Urban","year":"2016","journal-title":"arXiv preprint arXiv:1603.05691"},{"article-title":"Deep learning","year":"2016","author":"Goodfellow","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"author":"Krizhevsky","key":"ref25","article-title":"Cifar-10 (canadian institute for advanced research)"},{"author":"Krizhevsky","key":"ref26","article-title":"Cifar-100 (canadian institute for advanced research)"},{"key":"ref27","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"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS)","start":{"date-parts":[[2022,11,29]]},"location":"Ise, Japan","end":{"date-parts":[[2022,12,2]]}},"container-title":["2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10001867\/10001868\/10002143.pdf?arnumber=10002143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:58:43Z","timestamp":1709387923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10002143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/scisisis55246.2022.10002143","relation":{},"subject":[],"published":{"date-parts":[[2022,11,29]]}}}