{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:00:43Z","timestamp":1776679243819,"version":"3.51.2"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2017,5,24]],"date-time":"2017-05-24T00:00:00Z","timestamp":1495584000000},"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":["Commun. ACM"],"published-print":{"date-parts":[[2017,5,24]]},"abstract":"<jats:p>We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called \"dropout\" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.<\/jats:p>","DOI":"10.1145\/3065386","type":"journal-article","created":{"date-parts":[[2017,5,25]],"date-time":"2017-05-25T16:16:45Z","timestamp":1495729005000},"page":"84-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30823,"title":["ImageNet classification with deep convolutional neural networks"],"prefix":"10.1145","volume":"60","author":[{"given":"Alex","family":"Krizhevsky","sequence":"first","affiliation":[{"name":"Google Inc"}]},{"given":"Ilya","family":"Sutskever","sequence":"additional","affiliation":[{"name":"Google Inc"}]},{"given":"Geoffrey E.","family":"Hinton","sequence":"additional","affiliation":[{"name":"OpenAI"}]}],"member":"320","published-online":{"date-parts":[[2017,5,24]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345448.1345465"},{"key":"e_1_2_1_2_1","volume-title":"Large scale visual recognition challenge","author":"Berg A.","year":"2010"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_1_4_1","volume-title":"High-performance neural networks for visual object classification. Arxiv preprint arXiv:1102.0183","author":"Cire\u015fan D.","year":"2011"},{"key":"e_1_2_1_5_1","volume-title":"Multi-column deep neural networks for image classification. Arxiv preprint arXiv:1202.2745","author":"Cire\u015fan D.","year":"2012"},{"key":"e_1_2_1_6_1","unstructured":"Deng J. Berg A. Satheesh S. Su H. Khosla A. Fei-Fei L. In ILSVRC-2012 (2012).  Deng J. Berg A. Satheesh S. Su H. Khosla A. Fei-Fei L. In ILSVRC-2012 (2012)."},{"key":"e_1_2_1_7_1","volume-title":"CVPR09","author":"Deng J.","year":"2009"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2005.09.012"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"e_1_2_1_11_1","volume-title":"Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385","author":"He K.","year":"2015"},{"key":"e_1_2_1_12_1","volume-title":"Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580","author":"Hinton G.","year":"2012"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"e_1_2_1_14_1","volume-title":"Department of Computer Science","author":"Krizhevsky A.","year":"2009"},{"key":"e_1_2_1_15_1","volume-title":"Convolutional deep belief networks on cifar-10. Unpublished manuscript","author":"Krizhevsky A.","year":"2010"},{"key":"e_1_2_1_16_1","volume-title":"ESANN","author":"Krizhevsky A.","year":"2011"},{"key":"e_1_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems","author":"LeCun Y.","year":"1990"},{"key":"e_1_2_1_18_1","volume-title":"Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)","author":"LeCun Y.","year":"1985"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1896300.1896315"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01931367"},{"key":"e_1_2_1_23_1","volume-title":"Italy","author":"Mensink T.","year":"2012"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.0040027"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000579"},{"key":"e_1_2_1_27_1","volume-title":"DTIC Document","author":"Rumelhart D.E.","year":"1985"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995504"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/938980.939477"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2009.10-08-881"},{"key":"e_1_2_1_33_1","volume-title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences","author":"Werbos P.","year":"1974"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3065386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3065386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:05:20Z","timestamp":1750273520000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3065386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,24]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,5,24]]}},"alternative-id":["10.1145\/3065386"],"URL":"https:\/\/doi.org\/10.1145\/3065386","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,24]]},"assertion":[{"value":"2017-05-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}