{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T18:22:06Z","timestamp":1648923726034},"reference-count":19,"publisher":"MIT Press - Journals","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:p> Model-based classification of sequence data using a set of hidden Markov models is a well-known technique. The involved score function, which is often based on the class-conditional likelihood, can, however, be computationally demanding, especially for long data sequences. Inspired by recent theoretical advances in spectral learning of hidden Markov models, we propose a score function based on third-order moments. In particular, we propose to use the Kullback-Leibler divergence between theoretical and empirical third-order moments for classification of sequence data with discrete observations. The proposed method provides lower computational complexity at classification time than the usual likelihood-based methods. In order to demonstrate the properties of the proposed method, we perform classification of both simulated data and empirical data from a human activity recognition study. <\/jats:p>","DOI":"10.1162\/neco_a_01033","type":"journal-article","created":{"date-parts":[[2017,11,22]],"date-time":"2017-11-22T01:20:26Z","timestamp":1511313626000},"page":"216-236","source":"Crossref","is-referenced-by-count":0,"title":["Sequence Classification Using Third-Order Moments"],"prefix":"10.1162","volume":"30","author":[{"given":"Rasmus","family":"Troelsgaard","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby 2860, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars Kai","family":"Hansen","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby 2860, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","first-page":"2773","author":"Anandkumar A.","year":"2014","journal-title":"Journal of Machine Learning Research, 15"},{"key":"B2","first-page":"1","author":"Anandkumar A.","year":"2012","journal-title":"JMLR: Workshop and Conference Proceedings, 23"},{"key":"B3","first-page":"24","author":"Anguita D.","year":"2013","journal-title":"Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177697196"},{"issue":"3","key":"B5","first-page":"179","volume":"24","author":"Besag J.","year":"1975","journal-title":"Journal of the Royal Statistical Society. Series D"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(04)00162-1"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"B8","volume-title":"Random graph dynamics.","author":"Durrett R.","year":"2007"},{"key":"B9","first-page":"147","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Elkan C.","year":"2013"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177005981"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.268"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.12.025"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/080\/999014"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2009.22"},{"key":"B15","volume-title":"Proceedings of the IJCAI-99 Workshop on Neural, Symbolic and Reinforcement Learning Methods for Sequence Learning.","author":"Oates T.","year":"1999"},{"key":"B16","author":"Troelsgaard R.","year":"2016","journal-title":"Spectral learning of hidden Markov models in non-stationary data"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1115\/1.1475320"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s11416-006-0028-7"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1145\/1882471.1882478"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:42:13Z","timestamp":1615585333000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/30\/1\/216-236\/8331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1162\/neco_a_01033"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01033","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}