{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T15:11:59Z","timestamp":1698419519509},"reference-count":9,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":4462,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp;amp; Computers in Japan"],"published-print":{"date-parts":[[1995,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>When considering the algorithm of error backpropagation learning, it is seen that the learning of each layer is not completed independently. This paper proposes a DLBP learning algorithm which uses different learning coefficients for each layer. By changing the ratio of the learning coefficients, the following can be controlled: <jats:list list-type=\"explicit-label\">\n<jats:list-item><jats:p>the learning progress of the hidden units;<\/jats:p><\/jats:list-item>\n<jats:list-item><jats:p>the influence of the hidden units on the network. With DLBP learning, we can construct the corresponding networks to the different requirement such as;<\/jats:p><\/jats:list-item>\n<jats:list-item><jats:p>to obtain a network with small number of hidden units; and<\/jats:p><\/jats:list-item>\n<jats:list-item><jats:p>to obtain a fault tolerant network.<\/jats:p><\/jats:list-item>\n<\/jats:list><\/jats:p>","DOI":"10.1002\/scj.4690260705","type":"journal-article","created":{"date-parts":[[2007,7,8]],"date-time":"2007-07-08T09:18:25Z","timestamp":1183886305000},"page":"47-56","source":"Crossref","is-referenced-by-count":1,"title":["Backpropagation learning algorithm with different learning coefficients for each layer"],"prefix":"10.1002","volume":"26","author":[{"given":"Hirochika","family":"Takechi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Murakami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masanori","family":"Izumida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2007,3,21]]},"reference":[{"key":"e_1_2_1_2_2","volume-title":"D. E. Rumelhart and the PDF Research Group. Parallel Distributed Processing","author":"McClelland J. L.","year":"1986"},{"key":"e_1_2_1_3_2","unstructured":"H.TakechiandK.Murakami.Properties of backpropagation neural network by changing learning coefficients for each layer.Technical Report of I.E.I.C.E. Japan NC92\u201074 (Nov.1992)."},{"issue":"5","key":"e_1_2_1_4_2","first-page":"595","article-title":"A structural connections learning algorithm with forgetting. Jour","volume":"5","author":"Ishikawa M.","year":"1990","journal-title":"Artificial Intelligence Society"},{"issue":"6","key":"e_1_2_1_5_2","first-page":"812","article-title":"Backpropagation with artificial selection\u2014Reduction of the number of learning times and that of hidden units","volume":"74","author":"Hagiwara M.","year":"1991","journal-title":"Trans. I.E.I.C.E.(D\u2010II)"},{"key":"e_1_2_1_6_2","unstructured":"Y.TanandT.Nanya.Property of fault\u2010tolerant multilayer neural networks.Technical Report of I.E.I.C.E. Japan NC92\u201011 (May1992)."},{"key":"e_1_2_1_7_2","unstructured":"H.Nishida Y.MatsumotoandN.Okino.On learning algorithm for fault\u2010tolerant neural networks.Technical Report of I.E.I.C.E. Japan NC92\u201029 (July1992)."},{"key":"e_1_2_1_8_2","unstructured":"Y.TanandT.Nanya.A Note on Fault Tolerance in Multilayer Neural Networks. Proc. of the 42nd Conference of the Information Processing Society 6 pp.104\u2013105(1991)."},{"key":"e_1_2_1_9_2","unstructured":"H.TakechiandK.Murakami.On Influence of Partial Destruction of Back\u2010Propagation Neural Network.Proc. of the 1990 Joint Conf. of Shikoku Branch of Institutes of Electrical and Information Engineers 12\u20106(Oct.1990)."},{"key":"e_1_2_1_10_2","unstructured":"K.Niki.High speed BP learning method for binary pattern. Technical Report of I.E.I.C.E. Japan NC89\u20104 (May1989)."}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690260705","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690260705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T21:35:26Z","timestamp":1698356126000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690260705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1995,1]]},"references-count":9,"journal-issue":{"issue":"7","published-print":{"date-parts":[[1995,1]]}},"alternative-id":["10.1002\/scj.4690260705"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690260705","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1995,1]]}}}