{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T12:00:14Z","timestamp":1792756814597,"version":"4.5.0"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2012,8]]},"DOI":"10.1109\/tnnls.2012.2200299","type":"journal-article","created":{"date-parts":[[2012,6,11]],"date-time":"2012-06-11T14:02:10Z","timestamp":1339423330000},"page":"1177-1193","source":"Crossref","is-referenced-by-count":519,"title":["Twenty Years of Mixture of Experts"],"prefix":"10.1109","volume":"23","author":[{"given":"S. E.","family":"Yuksel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. N.","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P. D.","family":"Gader","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00014-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016737"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2002.1005474"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J R Stat Soc Ser B"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0114-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2010.5490217"},{"key":"ref37","article-title":"Boosting and random forest for visual recognition","author":"kim","year":"2009","journal-title":"Proc IEEE Conf Comput Vision (ICCV 2009)"},{"key":"ref36","author":"haykin","year":"1999","journal-title":"Neural Networks A Comprehensive Foundation"},{"key":"ref35","author":"hastie","year":"2001","journal-title":"The Elements of Statistical Learning Data Mining Inference and Prediction"},{"key":"ref34","author":"montillo","year":"2009","journal-title":"Statistical Foundations of Data Analysis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2010.5516203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/11427445_50"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394479"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.08.021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2008.4778956"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-S10-S6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39737-3_69"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.730"},{"key":"ref101","first-page":"3443","article-title":"Hierarchical mixtures of experts methodology applied to continuous speech recognition","volume":"5","author":"zhao","year":"1995","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref26","first-page":"2707","article-title":"A mixture of experts network structure for EEG signals classification","author":"guler","year":"2005","journal-title":"Proc 27th Annu Int Conf Eng Med Biol Soc"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007425814087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2004.05.018"},{"key":"ref50","first-page":"633","author":"xu","year":"1995","journal-title":"Advances in Neural Information Processing Systems 7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00043-X"},{"key":"ref59","first-page":"985","author":"jordan","year":"1991","journal-title":"Advances in neural information processing systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2006.05.022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488257"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/acs.744"},{"key":"ref55","first-page":"654","author":"tresp","year":"2001","journal-title":"Advances in Neural Information Processing Systems 13"},{"key":"ref54","first-page":"145","article-title":"Optimal model inference for Bayesian mixture of experts","volume":"1","author":"ueda","year":"2000","journal-title":"Proc IEEE Workshop Neural Netw Signal Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01510-6_109"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2007.06.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/B:NEPL.0000039425.58002.36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2003.1245713"},{"key":"ref6","first-page":"883","author":"meeds","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.09.050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq107"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1049\/cp:19950579","article-title":"pruning and growing hierachical mixtures of experts","author":"waterhouse","year":"1995","journal-title":"Proceedings of 4th International Conference on Artificial Neural Networks (Conf Publ No 409)"},{"key":"ref7","first-page":"1897","author":"yuan","year":"2009","journal-title":"Advances in Neural Information Processing Systems 21"},{"key":"ref9","author":"sminchisescu","year":"2004","journal-title":"Learning to reconstruct 3D human motion from Bayesian mixture of experts a probabilistic discriminative approach"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J R Stat Soc Ser B"},{"key":"ref45","first-page":"57","article-title":"Bayesian hierarchical mixtures of experts","author":"bishop","year":"2003","journal-title":"Proc 19th Conf Uncertain Artif Intell"},{"key":"ref48","author":"robert","year":"1998","journal-title":"Monte Carlo Statistical Methods"},{"key":"ref47","author":"mackay","year":"2003","journal-title":"Information Theory Inference and Learning Algorithms"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00154"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.839356"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00040-0"},{"key":"ref43","first-page":"351","author":"waterhouse","year":"1996","journal-title":"Advances in Neural Information Processing Systems 7"},{"key":"ref127","first-page":"1","article-title":"Application of mixture of experts model to financial time series forecasting","author":"cheung","year":"1995","journal-title":"Proc Int Conf Neural Netw Signal Process"},{"key":"ref126","first-page":"101","author":"gormley","year":"2011","journal-title":"Mixture of Experts Modelling with Social Science Applications"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.stamet.2010.01.002"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS178"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.1109\/ICNN.1995.488992","article-title":"Speaker identification based on the time-delay hierarchical mixture of experts","volume":"4","author":"chen","year":"1995","journal-title":"Proc IEEE Int Conf Neural Netw"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1994.366050"},{"key":"ref129","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1985.tb01327.x","article-title":"Some aspects of the spline smoothing approach to non-parametric curve fitting","volume":"47","author":"silverman","year":"1985","journal-title":"J Royal Stat Soc B"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-005-4787-7"},{"key":"ref128","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1002\/1099-131X(200007)19:4<375::AID-FOR779>3.0.CO;2-U","article-title":"Predicting daily probability distributions of S&#38;P500 returns","volume":"19","author":"weigend","year":"2000","journal-title":"J Forecast"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.598867"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-0450-1"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906875"},{"key":"ref77","author":"waterhouse","year":"1997","journal-title":"Classification and regression using Mixtures of Experts"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.826217"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1162\/089976602320264060"},{"key":"ref133","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v032.i06","article-title":"An R package for analyzing finite mixture models","volume":"32","author":"benaglia","year":"2009","journal-title":"J Stat Softw"},{"key":"ref131","author":"evers","year":"2007","journal-title":"HME Methods for Fitting Hierarchical Mixtures of Experts R Package Version 0 10"},{"key":"ref78","first-page":"1","author":"titterington","year":"2011","journal-title":"The EM Algorithm Variational Approximations and Expectation Propagation for Mixtures"},{"key":"ref132","year":"2012","journal-title":"The R Project for Statistical Computing"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.2.369"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.550800"},{"key":"ref62","author":"hinton","year":"2007","journal-title":"Introduction to Machine Learning Decision Trees and Mixtures of Experts"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21090-7_20"},{"key":"ref63","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065795000251"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.549080"},{"key":"ref66","first-page":"459","author":"fritsch","year":"1996","journal-title":"Advances in Neural Information Processing Systems 9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1996.10476965"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00050-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2006.73"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref109","volume":"9","author":"waterhouse","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref95","first-page":"719","author":"cacciatore","year":"1993","journal-title":"Advances in Neural Information Processing Systems 6"},{"key":"ref108","first-page":"14\/1","article-title":"learning in neural networks and stochastic approximation methods with averaging","author":"shcherbakov","year":"1994","journal-title":"IEE Colloquium on Advances in Neural Networks for Control and Systems (Digest No 1994\/136)"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/72.536325"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref93","doi-asserted-by":"crossref","first-page":"2015","DOI":"10.1109\/ICNN.1996.549211","article-title":"Combine multiple time-delay HMEs for speaker identification","volume":"4","author":"chen","year":"1996","journal-title":"Proc IEEE Int Conf Neural Netw"},{"key":"ref106","author":"breiman","year":"1984","journal-title":"Classification and Regression Trees"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/88.3.833"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s005210170004"},{"key":"ref91","first-page":"309","author":"zeevi","year":"1997","journal-title":"Advances in Neural Information Processing Systems 9"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1080\/095400999116241"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1162\/089976606774841594"},{"key":"ref103","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.21437\/Eurospeech.1997-521","article-title":"Improving performance on switchboard by combining hybrid HME\/HMM and mixture of Gaussians acoustic models","author":"fritsch","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref102","first-page":"1003","author":"meila","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347963"},{"key":"ref112","author":"nowlan","year":"1991","journal-title":"Advances in Neural Information Processing Systems 3"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/78.668782"},{"key":"ref98","first-page":"501","article-title":"Hidden Markov decision trees","author":"jordan","year":"1996","journal-title":"Proc Conf Adv Neural Inf Process Syst"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/72.536317"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1999.788138"},{"key":"ref97","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/3-540-70659-3_2","article-title":"Machine learning for sequential data: A review","author":"dietterich","year":"2002","journal-title":"Proc Joint IAPR Int Workshop Struct Syntactic Stat Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459461"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2007.01.009"},{"key":"ref13","first-page":"2178","author":"yao","year":"2009","journal-title":"Advances in Neural Information Processing Systems 22"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(02)00577-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.02.010"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.3115\/1117822.1117828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587578"},{"key":"ref82","first-page":"831","volume":"4","author":"vapnik","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref117","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/10.623058","article-title":"A patient-adaptable ECG beat classifier using a mixture of experts approach","volume":"44","author":"hu","year":"1997","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.12.002"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015367"},{"key":"ref18","first-page":"881","author":"rasmussen","year":"2002","journal-title":"Advances in Neural Information Processing Systems 14"},{"key":"ref84","author":"anthony","year":"1992","journal-title":"Computational Learning Theory An Introduction"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/72.857774"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4156\/jdcta.vol3.issue3.5"},{"key":"ref83","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref114","first-page":"1015","author":"hinton","year":"1995","journal-title":"Advances in Neural Information Processing Systems 7"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1993.716791"},{"key":"ref116","first-page":"459","article-title":"Customized ECG beat classifier using mixture of experts","author":"hu","year":"1995","journal-title":"Proc IEEE Workshop Neural Netw Signal Process"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/18.669150"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2009.57"},{"key":"ref120","author":"tuerk","year":"2001","journal-title":"The state based mixture of experts HMM with applications to the recognition of spontaneous speech"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143886"},{"key":"ref121","first-page":"845","author":"bregler","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1999.836243"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/3477.584952"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/18.841177"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00066-0"},{"key":"ref87","author":"casella","year":"2001","journal-title":"Statistical Inference"},{"key":"ref88","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1214\/aos\/1018031265","article-title":"Hierarchical mixtures-of-experts for exponential family regression models: Approximation and maximum likelihood estimation","volume":"27","author":"jiang","year":"1999","journal-title":"Ann Stat"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5962385\/6241418\/06215056.pdf?arnumber=6215056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T02:59:36Z","timestamp":1714013976000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6215056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,8]]},"references-count":133,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2012.2200299","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,8]]}}}