{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T05:12:38Z","timestamp":1775020358823,"version":"3.50.1"},"reference-count":10,"publisher":"MIT Press - Journals","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2001,12,1]]},"abstract":"<jats:p> This work concerns the selection of input-output pairs for improved training of multilayer perceptrons, in the context of approximation of univariate real functions. A criterion for the choice of the number of neurons in the hidden layer is also provided. The main idea is based on the fact that Chebyshev polynomials can provide approximations to bounded functions up to a prescribed tolerance, and, in turn, a polynomial of a certain order can be fitted with a three-layer perceptron with a prescribed number of hidden neurons. The results are applied to a sensor identification example. <\/jats:p>","DOI":"10.1162\/089976601317098484","type":"journal-article","created":{"date-parts":[[2002,7,27]],"date-time":"2002-07-27T11:56:30Z","timestamp":1027770990000},"page":"2673-2680","source":"Crossref","is-referenced-by-count":30,"title":["Specification of Training Sets and the Number of Hidden Neurons for Multilayer Perceptrons"],"prefix":"10.1162","volume":"13","author":[{"given":"L. S.","family":"Camargo","sequence":"first","affiliation":[]},{"given":"T.","family":"Yoneyama","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica, S. J. dos Campos, Brazil,"}]}],"member":"281","reference":[{"key":"p_2","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"p_3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993164"},{"key":"p_4","doi-asserted-by":"publisher","DOI":"10.1016\/S0898-1221(97)00169-7"},{"key":"p_6","doi-asserted-by":"publisher","DOI":"10.1109\/72.363453"},{"key":"p_8","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"p_10","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00068-8"},{"key":"p_15","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(96)00059-8"},{"key":"p_16","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(97)00097-X"},{"key":"p_18","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00068-9"},{"key":"p_19","doi-asserted-by":"publisher","DOI":"10.1109\/72.668889"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/089976601317098484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:48:46Z","timestamp":1615585726000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/13\/12\/2673-2680\/6547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,12,1]]},"references-count":10,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2001,12,1]]}},"alternative-id":["10.1162\/089976601317098484"],"URL":"https:\/\/doi.org\/10.1162\/089976601317098484","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,12,1]]}}}