{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T21:45:24Z","timestamp":1648935924860},"reference-count":9,"publisher":"MIT Press - Journals","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2000,6,1]]},"abstract":"<jats:p> The attractive possibility of applying layerwise block training algorithms to multilayer perceptrons MLP, which offers initial advantages in computational effort, is refined in this article by means of introducing a sensitivity correction factor in the formulation. This results in a clear performance advantage, which we verify in several applications. The reasons for this advantage are discussed and related to implicit relations with second-order techniques, natural gradient formulations through Fisher's information matrix, and sample selection. Extensions to recurrent networks and other research lines are suggested at the close of the article. <\/jats:p>","DOI":"10.1162\/089976600300015448","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T11:57:56Z","timestamp":1027771076000},"page":"1429-1447","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Block Training of Multilayer Perceptrons"],"prefix":"10.1162","volume":"12","author":[{"given":"A.","family":"Navia-V\u00e1zquez","sequence":"first","affiliation":[{"name":"DTC, Universidad Carlos III de Madrid, 28911-Legan\u00e9s (Madrid), Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. R.","family":"Figueiras-Vidal","sequence":"additional","affiliation":[{"name":"DTC, Universidad Carlos III de Madrid, 28911-Legan\u00e9s (Madrid), Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"p_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"p_2","doi-asserted-by":"publisher","DOI":"10.1109\/78.124956"},{"key":"p_4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.141"},{"key":"p_5","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80077-2"},{"key":"p_6","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)90066-3"},{"key":"p_7","doi-asserted-by":"publisher","DOI":"10.1109\/72.761724"},{"key":"p_17","doi-asserted-by":"publisher","DOI":"10.1109\/78.650102"},{"key":"p_19","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)90102-3"},{"key":"p_22","doi-asserted-by":"publisher","DOI":"10.1109\/72.501734"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/089976600300015448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:48:05Z","timestamp":1615585685000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/12\/6\/1429-1447\/6391"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000,6,1]]},"references-count":9,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2000,6,1]]}},"alternative-id":["10.1162\/089976600300015448"],"URL":"https:\/\/doi.org\/10.1162\/089976600300015448","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2000,6,1]]}}}