{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T04:58:33Z","timestamp":1698037113265},"reference-count":10,"publisher":"Wiley","issue":"1","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>This paper proposes a new neuron model \u201canalog coupled neuron (a\u2010CONE)\u201d with two sigmoid functions which is applied to parity and pattern recognition problems to show its ability. Also, a digital\u2010CONE (d\u2010CONE) capable of providing a digital output is proposed and it is trained by using a back propagation (BP)\u2010type algorithm. Moreover, it is shown that its speed of convergence in learning was faster than that of the standard BP. The a\u2010CONE presented here has two kinds of sigmoid functions <jats:italic>f<\/jats:italic><jats:sub>1<\/jats:sub> and <jats:italic>f<\/jats:italic><jats:sub>2<\/jats:sub> mapping an input into an output. The function <jats:italic>f<\/jats:italic><jats:sub>1<\/jats:sub> provides an output response of the neuron while the derivative in learning is given by both <jats:italic>f<\/jats:italic><jats:sub>1<\/jats:sub>\u2032 and <jats:italic>f<\/jats:italic><jats:sub>2<\/jats:sub>\u2032, where <jats:italic>f<\/jats:italic><jats:sub>1<\/jats:sub>\u2032 refers to the derivative of <jats:italic>f<\/jats:italic><jats:sub>1<\/jats:sub> with respect to weighted sum of input signals. This allows a fast convergence rate to be obtained in learning. From simulation results, it is shown that the a\u2010CONE has a rapid convergence rate in learning compared with the conventional BP and the learning algorithm of d\u2010CONE networks, and produces a noise\u2010tolerant mapping in the pattern recognition.<\/jats:p>","DOI":"10.1002\/scj.4690220110","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T19:35:04Z","timestamp":1183836904000},"page":"91-98","source":"Crossref","is-referenced-by-count":2,"title":["A new neuron model \u201ccone\u201d with fast convergence rate and its application to pattern recognition"],"prefix":"10.1002","volume":"22","author":[{"given":"Minoru","family":"Fukumi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sigeru","family":"Omatu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaru","family":"Teranishi","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","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing","author":"Rumelhart D. E.","year":"1986"},{"key":"e_1_2_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/29.1638"},{"key":"e_1_2_1_4_2","doi-asserted-by":"crossref","unstructured":"M.Hosokawa S.Omatu andM.Fukumi.A new approach for pattern recognition by neural networks with scramblers. Int. Joint Conf. on Neural Networks Washington D.C. (1989).","DOI":"10.1109\/IJCNN.1989.118578"},{"issue":"2","key":"e_1_2_1_5_2","first-page":"206","article-title":"Numeral character recognition by the algorithm of the neo\u2010cognitron","volume":"66","author":"Fukushima Kunihiko","year":"1983","journal-title":"Trans. I.E.C.E., Japan"},{"key":"e_1_2_1_6_2","unstructured":"N.Baba.A new approach for finding the global minimum of error function of neural networks. Proc. of the 28th SICE Annual Conf. ESS1\u20106 pp.1331\u20131334(1989)."},{"key":"e_1_2_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1989.118442"},{"key":"e_1_2_1_8_2","unstructured":"M.FukumiandS.Omatu.A new back\u2010propagation algorithm with coupled neuron and its application to pattern recognition. Proc. of the 28th SICE Annual Conf. ESS1\u20105 pp.1327\u20131330(1989)."},{"key":"e_1_2_1_9_2","unstructured":"MinoruFukumiandSigeruOmatu.Convergence property of a neuron model CONE with two sigmoid functions. Proc. of Shikoku Joint Conf. pp.379\u2013380 Shikoku Japan (1989)."},{"key":"e_1_2_1_10_2","volume-title":"Neural Computer","author":"Aihara Kazuyuki","year":"1988"},{"key":"e_1_2_1_11_2","volume-title":"Numerical Computation of Matrices","author":"Togawa Hayato","year":"1971"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690220110","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690220110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T00:05:56Z","timestamp":1698019556000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690220110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":10,"journal-issue":{"issue":"1","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690220110"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690220110","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]]}}}