{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T03:57:36Z","timestamp":1768967856899,"version":"3.49.0"},"reference-count":31,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[1998,8,1]],"date-time":"1998-08-01T00:00:00Z","timestamp":901929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[1998,8]]},"DOI":"10.1016\/s0893-6080(98)00087-2","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T12:59:42Z","timestamp":1027601982000},"page":"1059-1072","source":"Crossref","is-referenced-by-count":46,"title":["A modified back-propagation method to avoid false local minima"],"prefix":"10.1016","volume":"11","author":[{"given":"Yutaka","family":"Fukuoka","sequence":"first","affiliation":[]},{"given":"Hideo","family":"Matsuki","sequence":"additional","affiliation":[]},{"given":"Haruyuki","family":"Minamitani","sequence":"additional","affiliation":[]},{"family":"Akimasa Ishida","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0893-6080(98)00087-2_BIB1","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/72.105426","article-title":"Mean field annealing: A formalism for constructing GNC-like algorithms","volume":"3","author":"Bilbro","year":"1992","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB2","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoid function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Mathematics of Control, Signals, and Systems"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB3","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","article-title":"On the approximate realization of continuous mapping by neural networks","volume":"2","author":"Funahashi","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB4","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TPAMI.1984.4767596","article-title":"Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images","volume":"6","author":"Geman","year":"1984","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB5","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB6","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/79.180705","article-title":"Progress in supervised neural networks; What's new since Lippmann?","volume":"10","author":"Hush","year":"1993","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB7","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1109\/21.179853","article-title":"Error surfaces for multilayer","volume":"22","author":"Hush","year":"1992","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB8","doi-asserted-by":"crossref","unstructured":"Hush, D. R., & Salas, J. M. (1988). Improving the learning rate of back-propagation with the gradient reuse algorithm. In Proceedings of the IEEE Conference on Neural Networks (Vol. I, pp. 441\u2013447). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/ICNN.1988.23877"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB9","doi-asserted-by":"crossref","unstructured":"Irie, B., & Miyake, S. (1988). Capabilities of three-layered perceptions. In Proceedings of the IEEE Conference on Neural Networks (Vol. I, pp. 641\u2013648). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/ICNN.1988.23901"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB10","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/0893-6080(88)90003-2","article-title":"Increased rate of convergence through learning rate adaptation","volume":"1","author":"Jacobs","year":"1988","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB11","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1126\/science.220.4598.671","article-title":"Optimization by simulated annealing","volume":"220","author":"Kirkpatrick","year":"1983","journal-title":"Science"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB12","unstructured":"Kolen, J. F., & Pollack, J. B. (1991). Back propagation is sensitive to initial conditions. In R. P. Lippmann, J. E. Moody, & D. S. Tpuretzky (Eds.), Advances in Neural Information Processing Systems 3 (pp. 860\u2013867). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(98)00087-2_BIB13","unstructured":"Kramer, A. H., & Sangiovanni-Vincentelli, A. (1989). Efficient parallel learning algorithms for neural networks. In D. Touretzky (Ed.), Advances in Neural Information Processing Systems (pp. 40\u201348). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(98)00087-2_BIB14","doi-asserted-by":"crossref","unstructured":"Krzyzak, A., Dai, W., & Suen, C. Y. (1990). Classification of large set of handwritten characters using modified back propagation model. Proceedings of the International Joint Conference on Neural Networks (Vol. III, pp. 225\u2013232). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/IJCNN.1990.137849"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB15","doi-asserted-by":"crossref","unstructured":"Kung, S. Y., & Hwang, J. N. (1988). An algebraic projection analysis for optimal hidden units size and learning rates in back-propagation learning. In Proceedings of the IEEE Conference on Neural Networks (Vol. I, pp. 363\u2013370). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/ICNN.1988.23868"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB16","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/72.238314","article-title":"Paralleled hardware annealing for optimal solutions on electronic neural networks","volume":"4","author":"Lee","year":"1993","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB17","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1016\/S0893-6080(05)80116-9","article-title":"An analysis of premature saturation in back propagation learning","volume":"6","author":"Lee","year":"1993","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB18","doi-asserted-by":"crossref","unstructured":"McInerney, J. M., Haines, K. G., Biafore, S., & Hecht-Nielsen, R. (1989). Back propagation error surfaces can have local minima. In Proceedings of the International Joint Conference on Neural Networks (Vol. II, p. 627). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/IJCNN.1989.118524"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB19","doi-asserted-by":"crossref","unstructured":"Nguyen, D., & Widrow, B. (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In Proceedings of the International Joint Conference on Neural Networks (Vol. III, pp. 21\u201326). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/IJCNN.1990.137819"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB20","unstructured":"Parker, D. B. (1987). Optimal algorithms for adaptive networks: second order back propagation, second order direct propagation, and second order Hebbian learning. In Proceedings of the IEEE Conference on Neural Networks (Vol. II, pp. 593\u2013600). Piscataway, NJ: IEEE Press."},{"key":"10.1016\/S0893-6080(98)00087-2_BIB21","first-page":"995","article-title":"A mean field theory learning algorithm for neural networks","volume":"1","author":"Peterson","year":"1987","journal-title":"Complex Systems"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB22","unstructured":"Rezgui, A., & Tepedelenlioglu, N. (1990). The effect of the slope of the activation function on the back propagation algorithm. In Proceedings of the International Joint Conference on Neural Networks (Vol. I, pp. 707\u2013710). Piscataway, NJ: IEEE Press."},{"key":"10.1016\/S0893-6080(98)00087-2_BIB23","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/0893-6080(91)90006-Q","article-title":"Rescaling of variables in back propagation learning","volume":"4","author":"Rigler","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB24","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB25","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/0893-6080(92)90008-7","article-title":"Improving the convergence of the back-propagation algorithm","volume":"5","author":"van Ooyen","year":"1992","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB26","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/BF00332914","article-title":"Accelerating the convergence of the back-propagation method","volume":"59","author":"Vogl","year":"1988","journal-title":"Biological Cybernetics"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB27","unstructured":"Watrous, R. L., (1987). Learning algorithms for connectionist networks: applied gradient methods of nonlinear optimization. In Proceedings of the IEEE Conference on Neural Networks (Vol. II, pp. 619\u2013627). Piscataway, NJ: IEEE Press."},{"key":"10.1016\/S0893-6080(98)00087-2_BIB28","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/0893-6080(91)90073-E","article-title":"A method for self-determination of adaptive learning rates in back propagation","volume":"4","author":"Weir","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB29","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1109\/72.165592","article-title":"Avoiding false local minima by proper initialization of connections","volume":"3","author":"Wessels","year":"1992","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB30","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1142\/S0129065792000218","article-title":"Recent advances on techniques of static feedforward networks with supervised learning","volume":"3","author":"Xu","year":"1992","journal-title":"International Journal of Neural Systems"},{"key":"10.1016\/S0893-6080(98)00087-2_BIB31","doi-asserted-by":"crossref","unstructured":"Yamada, K., Kami, H., Tsukumo, J., & Temma, T. (1989). Handwritten numeral recognition by multilayer neural network with improved learning algorithm. In Proceedings of the International Joint Conference on Neural Networks (Vol. II, pp. 259\u2013266). Piscataway, NJ: IEEE Press.","DOI":"10.1109\/IJCNN.1989.118708"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608098000872?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608098000872?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,30]],"date-time":"2019-04-30T01:28:39Z","timestamp":1556587719000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608098000872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,8]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[1998,8]]}},"alternative-id":["S0893608098000872"],"URL":"https:\/\/doi.org\/10.1016\/s0893-6080(98)00087-2","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[1998,8]]}}}