{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T05:16:23Z","timestamp":1698124583295},"reference-count":13,"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":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>The backpropagation method is well known in the neural network and was proposed originally as a learning algorithm for the layered network composed of static nonlinear units. On the other hand, for problems such as those in control and signal processing where the time series is considered, the learning must be discussed in the network composed of dynamic units and containing feedback loops.<\/jats:p><jats:p>Pearlmutter discussed such a case and showed that a learning algorithm can be derived by introducing the adjoint system for the system obtained by linearizing the network. This is a natural extension of the ordinary backpropagation method.<\/jats:p><jats:p>This paper extends the method further and shows that a powerful learning algorithm is obtained for a very general neural network and evaluation function. By employing the proposed method, it is possible to realize the network with connection coefficients with a spatial structure, to determine the initial state of the network and to execute the learning for the input, not only for the connection coefficients.<\/jats:p>","DOI":"10.1002\/scj.4690221104","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T20:03:41Z","timestamp":1183838621000},"page":"31-41","source":"Crossref","is-referenced-by-count":2,"title":["Learning of neural networks using their adjoint systems"],"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","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"e_1_2_1_3_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.59.2229"},{"key":"e_1_2_1_4_2","first-page":"602","volume-title":"Generalization of back\u2010propagation to recurrent and higher\u2010order neural networks. Neural Information Processing Systems","author":"Pineda F. J.","year":"1988"},{"key":"e_1_2_1_5_2","first-page":"74","volume-title":"Backpropagation in non\u2010feedforward networks. Neural Computing Architectures","author":"Almeida L. B.","year":"1989"},{"key":"e_1_2_1_6_2","first-page":"149","volume-title":"Fixed point analysis for recurrent networks. Advances in Neural Information Processing Systems I","author":"Simard P. Y.","year":"1989"},{"key":"e_1_2_1_7_2","unstructured":"J.Barhen N.ToomarianandS.Gulati.Adjoint\u2010operator algorithms for learning in neural networks. Proc. IJCNN\u201090\u2010Wash.\u2010DC\u2010I pp.512\u2013516(1990)."},{"key":"e_1_2_1_8_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.263"},{"key":"e_1_2_1_9_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.81.10.3088"},{"key":"e_1_2_1_10_2","first-page":"29","article-title":"Generation of motion trajectory and learning system","volume":"24","author":"Uno Y.","year":"1988","journal-title":"Computrol"},{"key":"e_1_2_1_11_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3640537"},{"key":"e_1_2_1_12_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"e_1_2_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90022-1"},{"key":"e_1_2_1_14_2","doi-asserted-by":"crossref","unstructured":"M.Gherrity.A learning algorithm for analog fully recurrent neural networks. IJCNN Int. Joint Conf. on Neural Networks (1) pp.643\u2013644(1989).","DOI":"10.1109\/IJCNN.1989.118645"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690221104","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690221104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T05:09:22Z","timestamp":1698037762000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690221104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":13,"journal-issue":{"issue":"11","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690221104"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690221104","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]]}}}