{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T06:10:29Z","timestamp":1698127829272},"reference-count":8,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":5923,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp; Computers in Japan"],"published-print":{"date-parts":[[1991,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Backpropagation is one of the most widely used methods in artificial neural networks. The method determines the weights of connections between units in a layered network by an iterative computation so that the network produces desired outputs for given inputs. However, the resultant network does not necessarily provide reasonable outputs for patterns not given.<\/jats:p><jats:p>This paper proposes a modified back\u2010propagation learning that produces a reasonable input\u2010output relation for every possible input in which not only the error function between the actual output and the desired output but also the sensitivity of the output to the input variation are evaluated. It is shown also, using simple examples, that the method gives smooth mappings in the whole input space.<\/jats:p>","DOI":"10.1002\/scj.4690220211","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T20:30:16Z","timestamp":1183840216000},"page":"97-106","source":"Crossref","is-referenced-by-count":2,"title":["An approach to the generalization problem in the backpropagation method"],"prefix":"10.1002","volume":"22","author":[{"given":"Kiyotoshi","family":"Matsuoka","sequence":"first","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2007,3,21]]},"reference":[{"key":"e_1_2_1_2_2","volume-title":"Self\u2010Organization and Associative Memory","author":"Kohonen T.","year":"1983"},{"key":"e_1_2_1_3_2","doi-asserted-by":"crossref","unstructured":"S. K.KungandJ. N.Wang.An algebraic projection analysis for optimal hidden units size and learning rates in back\u2010propagation learning. Proc. Int. Conf. on Neural Networks I\u2013363\u2013370 (1988).","DOI":"10.1109\/ICNN.1988.23868"},{"key":"e_1_2_1_4_2","volume-title":"Generalized Inverse of Matrices and Its Applications","author":"Rao C. R.","year":"1971"},{"key":"e_1_2_1_5_2","doi-asserted-by":"crossref","first-page":"318","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing","author":"Rumelhart D. E.","year":"1986"},{"key":"e_1_2_1_6_2","doi-asserted-by":"crossref","unstructured":"J.SietsmaandR. J. F.Dow.Neural network pruning\u2014why and how. IEEE Int. Conf. on Neural Networks (I) pp.325\u2013333(1988).","DOI":"10.1109\/ICNN.1988.23864"},{"key":"e_1_2_1_7_2","volume-title":"Applied Linear Regression","author":"Weisberg S.","year":"1985"},{"key":"e_1_2_1_8_2","volume-title":"Mathematical principles of neural networks","author":"Amari S.","year":"1978"},{"key":"e_1_2_1_9_2","volume-title":"Regression Analysis","author":"Sawa T.","year":"1979"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690220211","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690220211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T07:15:53Z","timestamp":1698045353000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690220211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":8,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690220211"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690220211","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1991,1]]}}}