{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:58:22Z","timestamp":1782928702408,"version":"3.54.5"},"reference-count":18,"publisher":"MIT Press - Journals","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2010,12]]},"abstract":"<jats:p> Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. <\/jats:p>","DOI":"10.1162\/neco_a_00052","type":"journal-article","created":{"date-parts":[[2010,9,21]],"date-time":"2010-09-21T19:57:00Z","timestamp":1285099020000},"page":"3207-3220","source":"Crossref","is-referenced-by-count":713,"title":["Deep, Big, Simple Neural Nets for Handwritten Digit Recognition"],"prefix":"10.1162","volume":"22","author":[{"given":"Dan Claudiu","family":"Cire\u015fan","sequence":"first","affiliation":[{"name":"IDSIA, 6928 Manno-Lugano, Switzerland, and University of Lugano, 6900 Lugano, Switzerland, and Sculoa universitaria professionale della svizzera italiana, 6928 Manno-Lugano, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ueli","family":"Meier","sequence":"additional","affiliation":[{"name":"IDSIA, 6928 Manno-Lugano, Switzerland, and University of Lugano, 6900 Lugano, Switzerland, and Sculoa universitaria professionale della svizzera italiana, 6928 Manno-Lugano, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca Maria","family":"Gambardella","sequence":"additional","affiliation":[{"name":"IDSIA, 6928 Manno-Lugano, Switzerland, and University of Lugano, 6900 Lugano, Switzerland, and Sculoa universitaria professionale della svizzera italiana, 6928 Manno-Lugano, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[{"name":"IDSIA, 6928 Manno-Lugano, Switzerland, and University of Lugano, 6900 Lugano, Switzerland, and Sculoa universitaria professionale della svizzera italiana, 6928 Manno-Lugano, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"B1","first-page":"153","volume-title":"Advances in neural information processing systems","volume":"19","author":"Bengio Y.","year":"2006"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012454411458"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-6123(06)65034-6"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"B7","volume-title":"A field guide to dynamical recurrent neural networks","author":"Hochreiter S.","year":"2001"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.10.011"},{"key":"B10","first-page":"599","volume":"85","author":"LeCun Y.","year":"1985","journal-title":"Proceedings of Cognitiva, Paris"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"B13","volume-title":"Advances in neural information processing systems","volume":"21","author":"Nair V.","year":"2009"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"},{"key":"B16","volume-title":"Advances in neural information processing systems","volume":"19","author":"Ranzato M.","year":"2006"},{"key":"B17","volume-title":"Optimizing matrix transpose in CUDA","author":"Ruetsch G.","year":"2009"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel distributed processing","author":"Rumelhart D. E.","year":"1986"},{"key":"B19","volume-title":"Artificial intelligence: A modern approach","author":"Russell S.","year":"2002","edition":"2"},{"key":"B20","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Salakhutdinov R.","year":"2007"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"B23","first-page":"1115","volume-title":"Proceedings of the Eighth International Conference on Document Analysis and Recognition","author":"Steinkraus D.","year":"2005"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:25Z","timestamp":1615585105000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/22\/12\/3207-3220\/7596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":18,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2010,12]]}},"alternative-id":["10.1162\/NECO_a_00052"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00052","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,12]]}}}