Training radial basis functions by gradient descent

Training radial basis functions by gradient descent. Fernández-Redondo, M., Torres-Sospedra, J., Hernández-Espinosa, C., Ortiz-Gómez, M., & Torres-Sospedra, J. In IEEE International Conference on Neural Networks - Conference Proceedings, volume 3070, pages 184-189, 2004.

Website abstract bibtex

In this paper, we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of an unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training and we conclude that Online training suppose a reduction in the number of iterations. ©2006 IEEE.

@inProceedings{
 title = {Training radial basis functions by gradient descent},
 type = {inProceedings},
 year = {2004},
 identifiers = {[object Object]},
 pages = {184-189},
 volume = {3070},
 websites = {http://www.scopus.com/inward/record.url?eid=2-s2.0-9444257611&partnerID=tZOtx3y1,http://www.scopus.com/inward/record.url?eid=2-s2.0-40649101708&partnerID=tZOtx3y1},
 id = {a1f4db9b-8a16-3c63-8a04-fb8dd881f573},
 created = {2016-03-22T10:25:20.000Z},
 file_attached = {false},
 profile_id = {0a9a0ca7-e30a-305c-9a1e-1cc541ed5c45},
 group_id = {378eded2-9912-3700-bd6d-56be53368f0b},
 last_modified = {2016-03-22T10:25:20.000Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 abstract = {In this paper, we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of an unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training and we conclude that Online training suppose a reduction in the number of iterations. ©2006 IEEE.},
 bibtype = {inProceedings},
 author = {Fernández-Redondo, Mercedes and Torres-Sospedra, Joaquín and Hernández-Espinosa, Carlos and Ortiz-Gómez, Mamen and Torres-Sospedra, Joaquín},
 booktitle = {IEEE International Conference on Neural Networks - Conference Proceedings}
}

Downloads: 0

{"_id":"kj6isXf3Nx8mDPeF3","bibbaseid":"fernndezredondo-torressospedra-hernndezespinosa-ortizgmez-torressospedra-trainingradialbasisfunctionsbygradientdescent-2004","downloads":0,"creationDate":"2016-03-30T10:10:39.011Z","title":"Training radial basis functions by gradient descent","author_short":["Fernández-Redondo, M.","Torres-Sospedra, J.","Hernández-Espinosa, C.","Ortiz-Gómez, M.","Torres-Sospedra, J."],"year":2004,"bibtype":"inProceedings","biburl":null,"bibdata":{"title":"Training radial basis functions by gradient descent","type":"inProceedings","year":"2004","identifiers":"[object Object]","pages":"184-189","volume":"3070","websites":"http://www.scopus.com/inward/record.url?eid=2-s2.0-9444257611&partnerID=tZOtx3y1,http://www.scopus.com/inward/record.url?eid=2-s2.0-40649101708&partnerID=tZOtx3y1","id":"a1f4db9b-8a16-3c63-8a04-fb8dd881f573","created":"2016-03-22T10:25:20.000Z","file_attached":false,"profile_id":"0a9a0ca7-e30a-305c-9a1e-1cc541ed5c45","group_id":"378eded2-9912-3700-bd6d-56be53368f0b","last_modified":"2016-03-22T10:25:20.000Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"abstract":"In this paper, we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of an unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training and we conclude that Online training suppose a reduction in the number of iterations. ©2006 IEEE.","bibtype":"inProceedings","author":"Fernández-Redondo, Mercedes and Torres-Sospedra, Joaquín and Hernández-Espinosa, Carlos and Ortiz-Gómez, Mamen and Torres-Sospedra, Joaquín","booktitle":"IEEE International Conference on Neural Networks - Conference Proceedings","bibtex":"@inProceedings{\n title = {Training radial basis functions by gradient descent},\n type = {inProceedings},\n year = {2004},\n identifiers = {[object Object]},\n pages = {184-189},\n volume = {3070},\n websites = {http://www.scopus.com/inward/record.url?eid=2-s2.0-9444257611&partnerID=tZOtx3y1,http://www.scopus.com/inward/record.url?eid=2-s2.0-40649101708&partnerID=tZOtx3y1},\n id = {a1f4db9b-8a16-3c63-8a04-fb8dd881f573},\n created = {2016-03-22T10:25:20.000Z},\n file_attached = {false},\n profile_id = {0a9a0ca7-e30a-305c-9a1e-1cc541ed5c45},\n group_id = {378eded2-9912-3700-bd6d-56be53368f0b},\n last_modified = {2016-03-22T10:25:20.000Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n abstract = {In this paper, we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of an unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training and we conclude that Online training suppose a reduction in the number of iterations. ©2006 IEEE.},\n bibtype = {inProceedings},\n author = {Fernández-Redondo, Mercedes and Torres-Sospedra, Joaquín and Hernández-Espinosa, Carlos and Ortiz-Gómez, Mamen and Torres-Sospedra, Joaquín},\n booktitle = {IEEE International Conference on Neural Networks - Conference Proceedings}\n}","author_short":["Fernández-Redondo, M.","Torres-Sospedra, J.","Hernández-Espinosa, C.","Ortiz-Gómez, M.","Torres-Sospedra, J."],"urls":{"Website":"http://www.scopus.com/inward/record.url?eid=2-s2.0-9444257611&partnerID=tZOtx3y1,http://www.scopus.com/inward/record.url?eid=2-s2.0-40649101708&partnerID=tZOtx3y1"},"bibbaseid":"fernndezredondo-torressospedra-hernndezespinosa-ortizgmez-torressospedra-trainingradialbasisfunctionsbygradientdescent-2004","role":"author","downloads":0},"search_terms":["training","radial","basis","functions","gradient","descent","fernández-redondo","torres-sospedra","hernández-espinosa","ortiz-gómez","torres-sospedra"],"keywords":[],"authorIDs":[]}