{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T19:11:25Z","timestamp":1789931485461,"version":"4.0.1"},"reference-count":26,"publisher":"MIT Press - Journals","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2016,7]]},"abstract":"<jats:p>We present a mathematical construction for the restricted Boltzmann machine (RBM) that does not require specifying the number of hidden units. In fact, the hidden layer size is adaptive and can grow during training. This is obtained by first extending the RBM to be sensitive to the ordering of its hidden units. Then, with a carefully chosen definition of the energy function, we show that the limit of infinitely many hidden units is well defined. As with RBM, approximate maximum likelihood training can be performed, resulting in an algorithm that naturally and adaptively adds trained hidden units during learning. We empirically study the behavior of this infinite RBM, showing that its performance is competitive to that of the RBM, while not requiring the tuning of a hidden layer size.<\/jats:p>","DOI":"10.1162\/neco_a_00848","type":"journal-article","created":{"date-parts":[[2016,5,12]],"date-time":"2016-05-12T21:17:07Z","timestamp":1463087827000},"page":"1265-1288","source":"Crossref","is-referenced-by-count":45,"title":["An Infinite Restricted Boltzmann Machine"],"prefix":"10.1162","volume":"28","author":[{"given":"Marc-Alexandre","family":"C\u00f4t\u00e9","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Larochelle","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Universit\u00e9 de Sherbrooke, Sherbrooke, QC J1K 2R1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"B1","author":"Bastien F.","year":"2012","journal-title":"Theano: New features and speed improvements"},{"key":"B2","author":"Bergstra J.","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00397"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/516\/10172"},{"key":"B5","first-page":"679","volume-title":"Proceedings of the 29th International Conference on Machine Learning","author":"Dahl G. E.","year":"2012"},{"key":"B6","first-page":"145","volume":"9","author":"Desjardins G.","year":"2010","journal-title":"Proceedings of AISTATS"},{"key":"B7","first-page":"2121","volume":"12","author":"Duchi J.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B8","first-page":"524","volume-title":"Advances in neural information processing systems","volume":"2","author":"Fahlman S. E.","year":"1990"},{"key":"B9","first-page":"1242","author":"Gregor K.","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"B11","first-page":"29","author":"Larochelle H.","year":"2011","journal-title":"Proceedings of AISTATS"},{"key":"B12","first-page":"305","author":"Marlin B. M.","year":"2010","journal-title":"Proc. Intl. Conference on Artificial Intelligence and Statistics"},{"key":"B13","first-page":"1","volume":"23","author":"Montufar G.","year":"2010","journal-title":"Neural Computation"},{"key":"B14","first-page":"1137","volume-title":"Advances in neural information processing systems","volume":"21","author":"Murray I.","year":"2008"},{"key":"B15","volume-title":"Advances in information processing systems","volume":"21","author":"Nair V.","year":"2008"},{"key":"B16","volume-title":"Encyclopedia of machine learning","author":"Orbanz P.","year":"2010"},{"key":"B17","first-page":"1","volume-title":"Advances in neural information processing systems","author":"Raiko T.","year":"2014"},{"key":"B18","first-page":"621","volume":"9","author":"Ranzato M.","year":"2010","journal-title":"Journal of Machine Learning Research\u2014Proceedings Track"},{"key":"B20","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1145\/1273496.1273596","author":"Salakhutdinov R.","year":"2007","journal-title":"Proceedings of the 24th International Conference on Machine Learning"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390266"},{"key":"B22","first-page":"3293","volume-title":"Advances in neural information processing systems, 25","author":"Swersky K.","year":"2012"},{"key":"B23","first-page":"1025","volume":"12","author":"Taylor G. W.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390290"},{"key":"B25","first-page":"9","author":"Uria B.","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B26","first-page":"681","volume-title":"Advances in neural information processing systems, 15","author":"Welling M.","year":"2003"},{"key":"B27","first-page":"1453","volume-title":"Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics","author":"Zhou G.","year":"2012"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T06:12:16Z","timestamp":1655878336000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/28\/7\/1265-1288\/8166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":26,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2016,7]]}},"alternative-id":["10.1162\/NECO_a_00848"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00848","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}