{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:22:13Z","timestamp":1769314933564,"version":"3.49.0"},"reference-count":38,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[1998,6,1]],"date-time":"1998-06-01T00:00:00Z","timestamp":896659200000},"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":[[1998,6]]},"DOI":"10.1016\/s0893-6080(97)00134-2","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T18:54:47Z","timestamp":1027623287000},"page":"669-681","source":"Crossref","is-referenced-by-count":46,"title":["XOR has no local minima: A case study in neural network error surface analysis"],"prefix":"10.1016","volume":"11","author":[{"given":"Leonard G.C.","family":"Hamey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0893-6080(97)00134-2_BIB1","unstructured":"Auer, P., Herbster, M., Warmuth, M.K. (1996). Exponentially many local minima for single neurons. NeuroCOLT Technical Report No. NC-TR-96-030, University of London, Department of Computer Science, Egham, UK."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0893-6080(89)90014-2","article-title":"Neural networks and principal component analysis: Learning from examples without local minima","volume":"2","author":"Baldi","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB3","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1162\/neco.1989.1.4.532","article-title":"Approximation of boolean functions by sigmoidal networks: Part I: XOR and other two-variable functions","volume":"1","author":"Blum","year":"1989","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB4","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1109\/31.31314","article-title":"Back propagation fails to separate where perceptrons succeed","volume":"36","author":"Brady","year":"1989","journal-title":"IEEE Transactions on Circuits and Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB5","doi-asserted-by":"crossref","unstructured":"Cetin, B.C., Barhen, J., & Burdick, J.W. (1993a). Terminal repeller unconstrained subenergy tunneling (TRUST) for fast global optimization. Journal of Optimization Theory and Applications, 77, 97\u2013126.","DOI":"10.1007\/BF00940781"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB6","doi-asserted-by":"crossref","unstructured":"Cetin, B.C., Burdick, J.W., & Barhen, J. (1993b). Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks. In Proceedings of the IEEE International Conference on Neural Networks. IEEE, Piscataway, NJ, Vol. 2, pp. 836\u2013842.","DOI":"10.1109\/ICNN.1993.298667"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB7","unstructured":"Chauvin, Y. (1989). A back-propagation algorithm with optimal use of hidden units. In D.S. Touretzky (Ed.), Advances in neural information processing systems 1 (pp. 519\u2013526). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB8","unstructured":"Chauvin, Y. (1990). Dynamic behaviour of constrained back-propagation networks. In D.S. Touretzky (Ed.), Advances in neural information processing systems 2 (pp. 642\u2013649). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB9","unstructured":"Darken, C., & Moody, J. (1991). Note on learning rate schedules for stochastic optimization. In R.P. Lippman, J.E. Moody, & D.S. Touretzky (Eds.), Advances in neural information processing systems 3 (pp. 832\u2013838). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB10","unstructured":"Darken, C., & Moody, J. (1992). Towards faster stochastic gradient search. In J.E. Moody, S.J. Hanson, & R.P. Lippmann (Eds.), Advances in neural information processing systems 4 (pp. 1009\u20131016). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB11","unstructured":"Dayhoff, J.E. (1990). The exclusive-or: A classic problem. In Neural network architectures: An introduction (pp. 76\u201379). New York: Van Nostrand Reinhold."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB12","unstructured":"Gori, M., & Tesi, A. (1990). Some examples of local minima during learning with back-propagation. In Parallel architectures and neural networks: Third Italian workshop (pp. 87\u201394). Singapore: World Scientific."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB13","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/34.107014","article-title":"On the problem of local minima in backpropagation","volume":"14","author":"Gori","year":"1992","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB14","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1109\/72.317738","article-title":"Comments on \u201cCan backpropagation error surface not have local minima?\u201d","volume":"5","author":"Hamey","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB15","unstructured":"Hamey, L.G.C. (1995). The structure of neural network error surfaces. In M. Charles, & C. Latimer (Eds.), Proceedings of the Sixth Australian Conference on Neural Networks. University of Sydney, Department of Electrical Engineering, Sydney, Australia, pp. 197\u2013200."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB16","unstructured":"Hamey, L.G.C. (1996). Analysis of the error surface of the XOR network with two hidden nodes. In P. Bartlett, A. Burkitt, & R.C. Williamson (Eds.), Proceedings of the Seventh Australian Conference on Neural Networks. The Australian National University, Canberra, Australia, pp. 179\u2013183."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB17","unstructured":"Hanson, S.J., & Pratt, L.Y. (1989). Comparing biases for minimal network construction with back-propagation. In D.S. Touretzky (Ed.), Advances in neural information processing systems 1 (pp. 177\u2013185). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB18","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(89)90049-0","article-title":"Connectionist learning procedures","volume":"40","author":"Hinton","year":"1989","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB19","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1109\/21.179853","article-title":"Error surfaces for multilayer perceptrons","volume":"22","author":"Hush","year":"1992","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB20","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1142\/S0129065791000261","article-title":"Backpropagation learning for multilayer feed-forward neural networks using the conjugate gradient method","volume":"2","author":"Johansson","year":"1992","journal-title":"International Journal of Neural Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB21","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1088\/0954-898X\/3\/1\/005","article-title":"Comparison and evaluation of variants of the conjugate gradient method for efficient learning in feed-forward neural networks with backward error propagation","volume":"3","author":"Kinsella","year":"1992","journal-title":"Network: Computation in Neural Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB22","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(97)00134-2_BIB23","first-page":"269","article-title":"Back propagation is sensitive to initial conditions","volume":"4","author":"Kolen","year":"1990","journal-title":"Complex Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB24","unstructured":"Kramer, A.H., & Sangiovanni-Vincentelli, A. (1989). Efficient parallel learning algorithms for neural networks. In D.S. Touretzky (Ed.), Advances in neural information processing systems 1 (pp. 40\u201348). San Mateo, CA: Morgan Kaufmann."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB25","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1088\/0954-898X\/2\/1\/007","article-title":"Complete solution of the local minima in the XOR problem","volume":"2","author":"Lisboa","year":"1991","journal-title":"Network: Computation in Neural Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB26","unstructured":"Luenberger, D.G. (1984). Linear and nonlinear programming. Reading, MA: Addison-Wesley."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB27","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/S0893-6080(05)80056-5","article-title":"A scaled conjugate gradient algorithm for fast supervised learning","volume":"6","author":"M\u00f8ller","year":"1993","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB28","unstructured":"Orchard, G.A., & Phillips, W.A. (1991). Neural computation: A beginner's guide. London: Erlbaum."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB29","doi-asserted-by":"crossref","unstructured":"Poston, T., Lee, C.-N., Choie, Y., & Kwon, Y. (1991). Local minima and back propagation. In International Joint Conference on Neural Networks (Vol. 2, pp. 173\u2013176). New York: IEEE.","DOI":"10.1109\/IJCNN.1991.155333"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB30","unstructured":"Rumelhart, D.E., Hinton, G.E., & Williams, R.J. (1986). Learning internal representations by error propagation. In Parallel distributed processing (pp. 318\u2013362). Cambridge, MA: MIT Press."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB31","first-page":"91","article-title":"Backpropagation can give rise to spurious local minima even for networks without hidden layers","volume":"3","author":"Sontag","year":"1989","journal-title":"Complex Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB32","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/0893-6080(91)90008-S","article-title":"Back propagation separates where perceptrons do","volume":"4","author":"Sontag","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB33","unstructured":"Sprinkhuizen-Kuyper, I.G., & Boers, E.J.W. (1994). A comment on a paper of Blum: Blum's `local minima' are saddle points. Tech. Rep. No. 94-34, Leiden University, Department of Computer Science, Leiden, The Netherlands."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB34","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1162\/neco.1996.8.6.1301","article-title":"The error surface of the simplest XOR network has only global minima","volume":"8","author":"Sprinkhuizen-Kuyper","year":"1996","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB35","unstructured":"Wasserman, P.D. (1989). Neural computing: Theory and practice. New York: Van Nostrand Reinhold."},{"key":"10.1016\/S0893-6080(97)00134-2_BIB36","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1142\/S0129065790000102","article-title":"Predicting the future: A connectionist approach","volume":"1","author":"Weigend","year":"1990","journal-title":"International Journal of Neural Systems"},{"key":"10.1016\/S0893-6080(97)00134-2_BIB37","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(97)00134-2_BIB38","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1109\/72.410380","article-title":"On the local minima free condition of backpropagation learning","volume":"6","author":"Yu","year":"1995","journal-title":"IEEE Transactions on Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608097001342?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608097001342?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,18]],"date-time":"2019-04-18T13:27:29Z","timestamp":1555594049000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608097001342"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,6]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[1998,6]]}},"alternative-id":["S0893608097001342"],"URL":"https:\/\/doi.org\/10.1016\/s0893-6080(97)00134-2","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[1998,6]]}}}