{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T05:40:32Z","timestamp":1698471632369},"reference-count":22,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":4097,"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":[[1996,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper proposes the Recurrent SOLAR (Supervised One\u2010shot Learning Algorithm for Real number inputs) algorithm, that can complete learning by a single presentation of analog time series data. The most remarkable feature of the Recurrent SOLAR is the one\u2010shot learning, which has been difficult in the past modes, and which can be completed with a high speed by a single presentation of the time\u2010series input data composed of real numbers. The basic idea of the Recurrent SOLAR is the same as in the context model. The time is considered as discrete, and the connection weight of the feedback loop from the output unit or the hidden unit to the state units is fixed. Consequently, the recurrent network can be considered as a feed\u2010forward network.<\/jats:p><jats:p>The backpropagation algorithm is used in the context model, while the SOLAR algorithm is applied to the Recurrent SOLAR, which is the one\u2010shot learning algorithm based on the pattern recognition theory. By the use of the SOLAR algorithm, the Recurrent SOLAR can learn the analog time\u2010series data by a single presentation without falling in a local minimum even for large\u2010scale data. In other words, it is a learning algorithm that is suited to an environment where high speed is required in the learning.<\/jats:p>","DOI":"10.1002\/scj.4690271109","type":"journal-article","created":{"date-parts":[[2007,7,8]],"date-time":"2007-07-08T09:54:18Z","timestamp":1183888458000},"page":"97-110","source":"Crossref","is-referenced-by-count":0,"title":["Recurrent SOLAR algorithm"],"prefix":"10.1002","volume":"27","author":[{"given":"Kosei","family":"Demura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichiro","family":"Anzai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Kajiura","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","unstructured":"K.DemuraandY.Anzai.Improving the generalization ability of one\u2010shot algorithm. In: Proc. of International Conference on Neural Information Processing pp.195\u2013200(1994)."},{"issue":"10","key":"e_1_2_1_3_2","first-page":"2083","article-title":"Supervised one\u2010shot learning algorithm for real number inputs","volume":"77","author":"Demura K.","year":"1994","journal-title":"Trans. (D\u2010II) I.E.I.C.E., Japan"},{"key":"e_1_2_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90022-1"},{"key":"e_1_2_1_5_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"e_1_2_1_6_2","unstructured":"T.Iijima.Theory of discrimination by multiple similarity method.Tech. Rep. I.E.I.C.E. Japan PRL74 24 (1974)."},{"key":"e_1_2_1_7_2","volume-title":"Theory of Pattern Recognition","author":"Iijima T.","year":"1989"},{"issue":"6","key":"e_1_2_1_8_2","first-page":"365","article-title":"A general structural learning of connectionist modes using forgetting","volume":"112","author":"Ishikawa M.","year":"1992","journal-title":"Trans. IEEJ, Japan"},{"key":"e_1_2_1_9_2","unstructured":"T.MoriyamaandM.Ishikawa.Prediction of time series based on the structural learning of neural networks. In: Proc. of International Conference on Neural Information Processing pp.836\u2013841(1994)."},{"key":"e_1_2_1_10_2","unstructured":"M.Jordan.A parallel distributed processing approach.ICS report8604 UC San Diego (1986)."},{"key":"e_1_2_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.265958"},{"key":"e_1_2_1_12_2","unstructured":"A.Namatame.Structured neural networks and their flash learning. In: Proc. Workshop Algorithmic Learning Theory pp.67\u201380(1990)."},{"key":"e_1_2_1_13_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065792000036"},{"key":"e_1_2_1_14_2","doi-asserted-by":"crossref","unstructured":"E.OjaandJ.Karhunen.An analysis of convergence for a learning version of the subspace method. J. Math. Anal. Appl. pp.102\u2013111(1983).","DOI":"10.1016\/0022-247X(83)90095-1"},{"key":"e_1_2_1_15_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.263"},{"key":"e_1_2_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00198101"},{"key":"e_1_2_1_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.243"},{"key":"e_1_2_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/7902.7906"},{"key":"e_1_2_1_19_2","first-page":"113","volume-title":"Advance in Neural Information Processing System","author":"Toomarian N.","year":"1991"},{"issue":"5","key":"e_1_2_1_20_2","first-page":"1055","article-title":"Experimental studies of memory surfaces and learning surfaces in recurrent neural networks","volume":"76","author":"Watanabe T.","year":"1993","journal-title":"Trans. (D\u2010II) I.E.I.C.E., Japan"},{"key":"e_1_2_1_21_2","doi-asserted-by":"crossref","unstructured":"P. J.Werbos.Backpropagation through time: what it does and how to do it.Proceedings of the IEEE 78 10 pp.1550\u20131560(1990).","DOI":"10.1109\/5.58337"},{"key":"e_1_2_1_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"issue":"6","key":"e_1_2_1_23_2","first-page":"1289","article-title":"Valley searching method for recurrent nerual networks","volume":"76","author":"Yokoi K.","year":"1993","journal-title":"Trans. (D\u2010II) I.E.I.C.E., Japan"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690271109","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690271109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T02:54:58Z","timestamp":1698375298000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690271109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996,1]]},"references-count":22,"journal-issue":{"issue":"11","published-print":{"date-parts":[[1996,1]]}},"alternative-id":["10.1002\/scj.4690271109"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690271109","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1996,1]]}}}