{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:28:57Z","timestamp":1778084937959,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T00:00:00Z","timestamp":1713916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,24]]},"DOI":"10.1145\/3665065.3665071","type":"proceedings-article","created":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T12:21:46Z","timestamp":1722687706000},"page":"31-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":61,"title":["Accelerating Neural Network Training: A Brief Review"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2404-6963","authenticated-orcid":false,"given":"Sahil","family":"Nokhwal","sequence":"first","affiliation":[{"name":"Computer Science Dept., University of Memphis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6237-7056","authenticated-orcid":false,"given":"Priyanka","family":"Chilakalapudi","sequence":"additional","affiliation":[{"name":"Computer Science Dept., University of Memphis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2278-9196","authenticated-orcid":false,"given":"Preeti","family":"Donekal","sequence":"additional","affiliation":[{"name":"Data Science Dept., University of Memphis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6220-7780","authenticated-orcid":false,"given":"Suman","family":"Nokhwal","sequence":"additional","affiliation":[{"name":"Staff Engineer, Intercontinental Exchange, Inc., USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5435-5188","authenticated-orcid":false,"given":"Saurabh","family":"Pahune","sequence":"additional","affiliation":[{"name":"Software Engineer, Cardinal Health, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7510-1963","authenticated-orcid":false,"given":"Ankit","family":"Chaudhary","sequence":"additional","affiliation":[{"name":"Associate Professor, Jawaharlal Nehru University, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2018.8612873"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_4_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)","author":"Handral Praneeta","year":"2022","unstructured":"Praneeta Handral, Ritika Kulkarni, Swapna MD, and Nikhil Kumar. 2022. CIFAR-10 Image Classification with Convolutional Neural Networks. International Journal of Advanced Research in Science, Communication and Technology (IJARSCT) (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Deep residual learningfor image recognition. ComputerScience","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learningfor image recognition. ComputerScience (2015)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","volume-title":"Improving generalization performance by switching from adam to sgd. arXiv preprint arXiv:1712.07628","author":"Keskar Nitish\u00a0Shirish","year":"2017","unstructured":"Nitish\u00a0Shirish Keskar and Richard Socher. 2017. Improving generalization performance by switching from adam to sgd. arXiv preprint arXiv:1712.07628 (2017)."},{"key":"e_1_3_2_1_9_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_10_1","unstructured":"Alex Krizhevsky Geoffrey Hinton 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_11_1","volume-title":"Mixed precision training. arXiv preprint arXiv:1710.03740","author":"Micikevicius Paulius","year":"2017","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, 2017. Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218700"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852422"},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105\u20136114."},{"key":"e_1_3_2_1_15_1","volume-title":"A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867","author":"Zhai Xiaohua","year":"2019","unstructured":"Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre\u00a0Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, 2019. A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867 (2019)."}],"event":{"name":"ISMSI 2024: 2024 8th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","location":"Singapore Singapore","acronym":"ISMSI 2024"},"container-title":["2024 8th International Conference on Intelligent Systems Metaheuristics & Swarm Intelligence (ISMSI)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665065.3665071","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665065.3665071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:22:02Z","timestamp":1756236122000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665065.3665071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,24]]},"references-count":15,"alternative-id":["10.1145\/3665065.3665071","10.1145\/3665065"],"URL":"https:\/\/doi.org\/10.1145\/3665065.3665071","relation":{},"subject":[],"published":{"date-parts":[[2024,4,24]]},"assertion":[{"value":"2024-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}