{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:37:41Z","timestamp":1791394661192,"version":"4.3.3"},"publisher-location":"Berlin, Heidelberg","reference-count":46,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540231226","type":"print"},{"value":"9783540286509","type":"electronic"}],"license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-28650-9_7","type":"book-chapter","created":{"date-parts":[[2010,2,25]],"date-time":"2010-02-25T18:49:29Z","timestamp":1267123769000},"page":"146-168","source":"Crossref","is-referenced-by-count":147,"title":["Stochastic Learning"],"prefix":"10.1007","author":[{"given":"L\u00e9on","family":"Bottou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"7_CR1","volume-title":"Differential-geometrical methods in statistics","author":"S.-I. Amari","year":"1990","unstructured":"Amari, S.-I.: Differential-geometrical methods in statistics. Springer, Berlin (1990)"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1109\/PGEC.1967.264666","volume":"EC-16","author":"S.I. Amari","year":"1967","unstructured":"Amari, S.I.: A theory of adaptive pattern classifiers. IEEE Transactions on Electronic Computers\u00a0EC-16, 299\u2013307 (1967)","journal-title":"IEEE Transactions on Electronic Computers"},{"key":"7_CR3","first-page":"127","volume-title":"Neural Information Processing Systems","author":"S.-I. Amari","year":"1996","unstructured":"Amari, S.-I.: Natural learning in structured parameter spaces \u2013 natural riemannian gradient. In: Neural Information Processing Systems, vol.\u00a09, pp. 127\u2013133. MIT Press, Cambridge (1996)"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1162\/neco.1992.4.2.141","volume":"4","author":"R. Battiti","year":"1992","unstructured":"Battiti, R.: First- and second-order methods for learning: Between steepest descent and newton\u2019s method. Neural Computation\u00a04, 141\u2013166 (1992)","journal-title":"Neural Computation"},{"key":"7_CR5","first-page":"29","volume-title":"Proceedings of the 1988 Connectionist Models Summer School","author":"S. Becker","year":"1989","unstructured":"Becker, S., Le Cun, Y.: Improving the convergence of back-propagation learning with second-order methods. In: Touretzky, D., Hinton, G., Sejnowski, T. (eds.) Proceedings of the 1988 Connectionist Models Summer School, pp. 29\u201337. Morgan Kaufmann, San Mateo (1989)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Bengio, Y., LeCun, Y., Nohl, C., Burges, C.: Lerec: A nn\/hmm hybrid for on-line handwriting recognition. Neural Computation\u00a07(6) (November 1995)","DOI":"10.1162\/neco.1995.7.6.1289"},{"key":"7_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75894-2","volume-title":"Adaptive Algorithms and Stochastic Approximations","author":"A. Benveniste","year":"1990","unstructured":"Benveniste, A., Metivier, M., Priouret, P.: Adaptive Algorithms and Stochastic Approximations. Springer, Berlin (1990)"},{"key":"7_CR8","first-page":"489","volume-title":"Proc. of Computer Vision and Pattern Recognition","author":"L. Bottou","year":"1997","unstructured":"Bottou, L., Le Cun, Y., Bengio, Y.: Global training of document processing systems using graph transformer networks. In: Proc. of Computer Vision and Pattern Recognition, pp. 489\u2013493. IEEE, Puerto-Rico (1997)"},{"key":"7_CR9","unstructured":"Bottou, L.: Une Approche th\u00e9orique de l\u2019Apprentissage Connexionniste: Applications \u00e0 la Reconnaissance de la Parole. PhD thesis, Universit\u00e9 de Paris XI, Orsay, France (1991)"},{"key":"7_CR10","volume-title":"Online Learning and Neural Networks","author":"L. Bottou","year":"1998","unstructured":"Bottou, L.: Online algorithms and stochastic approximations. In: Saad, D. (ed.) Online Learning and Neural Networks. Cambridge University Press, Cambridge (1998)"},{"key":"7_CR11","volume-title":"Advances in Neural Information Processing Systems","author":"L. Bottou","year":"1995","unstructured":"Bottou, L., Bengio, Y.: Convergence properties of the kmeans algorithm. In: Advances in Neural Information Processing Systems, Denver, vol.\u00a07. MIT Press, Cambridge (1995)"},{"key":"7_CR12","volume-title":"Advances in Neural Information Processing Systems","author":"L. Bottou","year":"2004","unstructured":"Bottou, L., Le Cun, Y.: Large scale online learning. In: Advances in Neural Information Processing Systems, vol.\u00a016. MIT Press, Cambridge (2004)"},{"key":"7_CR13","unstructured":"Bottou, L., Le Cun, Y.: On-line learning for very large datasets. In: Applied Stochastic Models in Business and Industry, Special issue (to appear, 2004)"},{"key":"7_CR14","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"L. Bottou","year":"2002","unstructured":"Bottou, L., Murata, N.: Stochastic approximations and efficient learning. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, 2nd edn. The MIT Press, Cambridge (2002)","edition":"2"},{"key":"7_CR15","volume-title":"Numerical Methods For Unconstrained Optimization and Nonlinear Equations","author":"J.E. Dennis Jr.","year":"1983","unstructured":"Dennis Jr., J.E., Schnabel, R.B.: Numerical Methods For Unconstrained Optimization and Nonlinear Equations. Prentice-Hall, Inc., Englewood Cliffs (1983)"},{"key":"7_CR16","volume-title":"Pattern Classification And Scene Analysis","author":"R.O. Duda","year":"1973","unstructured":"Duda, R.O., Hart, P.E.: Pattern Classification And Scene Analysis. Wiley and Sons, Chichester (1973)"},{"key":"7_CR17","first-page":"231","volume-title":"Neural Information Processing Systems","author":"C. Gentile","year":"1999","unstructured":"Gentile, C., Warmuth, M.K.: Linear hinge loss and average margin. In: Neural Information Processing Systems, vol.\u00a011, pp. 231\u2013255. MIT Press, Cambridge (1999)"},{"key":"7_CR18","volume-title":"The Organization of Behavior","author":"D.O. Hebb","year":"1949","unstructured":"Hebb, D.O.: The Organization of Behavior. Wiley, New York (1949)"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/BF00337288","volume":"43","author":"T. Kohonen","year":"1982","unstructured":"Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics\u00a043, 59\u201369 (1982)","journal-title":"Biological Cybernetics"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Kohonen, T., Barna, G., Chrisley, R.: Statistical pattern recognition with neural network: Benchmarking studies. In: Proceedings of the IEEE Second International Conference on Neural Networks, San Diego, vol.\u00a01, pp. 61\u201368 (1988)","DOI":"10.1109\/ICNN.1988.23829"},{"key":"7_CR21","unstructured":"Krasovskii, A.A.: Dynamic of continuous self-Organizing Systems. Fizmatgiz, Moscow (1963) (in russian)"},{"key":"7_CR22","volume-title":"Applied Math. Sci.","author":"H.J. Kushner","year":"1978","unstructured":"Kushner, H.J., Clark, D.S.: Stochastic Approximation for Constrained and Unconstrained Systems. In: Applied Math. Sci., vol.\u00a026. Springer, Berlin, New York (1978)"},{"issue":"4","key":"7_CR23","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y. Le Cun","year":"1989","unstructured":"Le Cun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation\u00a01(4), 541\u2013551 (1989) (Winter)","journal-title":"Neural Computation"},{"issue":"11","key":"7_CR24","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y. Cun Le","year":"1998","unstructured":"Le Cun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient based learning applied to document recognition. Proceedings of IEEE\u00a086(11), 2278\u20132324 (1998)","journal-title":"Proceedings of IEEE"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","volume-title":"Neural Networks: Tricks of the Trade","author":"Y.A. LeCun","year":"1998","unstructured":"LeCun, Y.A., Bottou, L., Orr, G.B., M\u00fcller, K.-R.: Efficient backProp. In: Orr, G.B., M\u00fcller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol.\u00a01524, p. 9. Springer, Heidelberg (1998)"},{"key":"7_CR26","volume-title":"Proc. of Computer Vision and Pattern Recognition","author":"Y. Cun Le","year":"2004","unstructured":"Le Cun, Y., Bottou, L., HuangFu, J.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proc. of Computer Vision and Pattern Recognition, Washington, D.C. IEEE, Los Alamitos (2004)"},{"key":"7_CR27","volume-title":"Theory and Practice of recursive identification","author":"L. Ljung","year":"1983","unstructured":"Ljung, L., S\u00f6derstr\u00f6m, T.: Theory and Practice of recursive identification. MIT Press, Cambridge (1983)"},{"key":"7_CR28","first-page":"281","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematics, Statistics, and Probabilities","author":"J. MacQueen","year":"1967","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: LeCam, L.M., Neyman, J. (eds.) Proceedings of the Fifth Berkeley Symposium on Mathematics, Statistics, and Probabilities, vol.\u00a01, pp. 281\u2013297. University of California Press, Berkeley and Los Angeles (Calif) (1967)"},{"key":"7_CR29","volume-title":"Perceptrons","author":"M. Minsky","year":"1969","unstructured":"Minsky, M., Papert, S.: Perceptrons. MIT Press, Cambridge (1969)"},{"issue":"1","key":"7_CR30","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/72.363436","volume":"6","author":"U. M\u00fcller","year":"1995","unstructured":"M\u00fcller, U., Gunzinger, A., Guggenb\u00fchl, W.: Fast neural net simulation with a DSP processor array. IEEE Trans. on Neural Networks\u00a06(1), 203\u2013213 (1995)","journal-title":"IEEE Trans. on Neural Networks"},{"issue":"1","key":"7_CR31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0165-1684(98)00206-0","volume":"74","author":"N. Murata","year":"1999","unstructured":"Murata, N., Amari, S.-i.: Statistical analysis of learning dynamics. Signal Processing\u00a074(1), 3\u201328 (1999)","journal-title":"Signal Processing"},{"key":"7_CR32","first-page":"351","volume-title":"Proceedings of the 1993 Connectionist Models Summer School","author":"G.B. Orr","year":"1994","unstructured":"Orr, G.B., Leen, T.K.: Momentum and optimal stochastic search. In: Mozer, M.C., Smolensky, P., Touretzky, D.S., Elman, J.L., Weigend, A.S. (eds.) Proceedings of the 1993 Connectionist Models Summer School, pp. 351\u2013357. Lawrence Erlbaum Associates, Mahwah (1994)"},{"key":"7_CR33","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H. Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation model. Ann. Math. Stat.\u00a022, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"7_CR34","unstructured":"Rosenblatt, F.: The perceptron: A perceiving and recognizing automaton. Technical Report 85-460-1, Project PARA, Cornell Aeronautical Lab (1957)"},{"key":"7_CR35","doi-asserted-by":"crossref","first-page":"318","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel distributed processing: Explorations in the microstructure of cognition","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel distributed processing: Explorations in the microstructure of cognition, vol.\u00a0I, pp. 318\u2013362. Bradford Books, Cambridge (1986)"},{"key":"7_CR36","volume-title":"Advances in Neural Information Processing Systems","author":"J.Z.S. Rosset","year":"2004","unstructured":"Rosset, J.Z.S., Hastie, T.: Margin maximizing loss functions. In: Advances in Neural Information Processing Systems, vol.\u00a016. MIT Press, Cambridge (2004)"},{"key":"7_CR37","unstructured":"Schenkel, M., Weissman, H., Guyon, I., Nohl, C., Henderson, D.: Recognition-based segmentation of on-line hand-printed words. In: Hanson, S.J., Cowan, J.D., Giles, C.L. (eds.) Advances in Neural Information Processing Systems, Denver, CO, vol.\u00a05, pp. 723\u2013730 (1993)"},{"key":"7_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1007\/3-540-46084-5_218","volume-title":"Artificial Neural Networks - ICANN 2002","author":"N.N. Schraudolph","year":"2002","unstructured":"Schraudolph, N.N., Graepel, T.: Conjugate directions for stochastic gradient descent. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol.\u00a02415, p. 1351. Springer, Heidelberg (2002)"},{"key":"7_CR39","first-page":"145","volume":"1","author":"T.J. Sejnowski","year":"1987","unstructured":"Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce english text. Complex Systems\u00a01, 145\u2013168 (1987)","journal-title":"Complex Systems"},{"key":"7_CR40","volume-title":"Adaptation and Learning in automatic systems","author":"Y. Tsypkin","year":"1971","unstructured":"Tsypkin, Y.: Adaptation and Learning in automatic systems. Academic Press, New York (1971)"},{"key":"7_CR41","volume-title":"Foundations of the theory of learning systems","author":"Y. Tsypkin","year":"1973","unstructured":"Tsypkin, Y.: Foundations of the theory of learning systems. Academic Press, New York (1973)"},{"key":"7_CR42","series-title":"Series in Statistics","volume-title":"Estimation of dependences based on empirical data","author":"V.N. Vapnik","year":"1982","unstructured":"Vapnik, V.N.: Estimation of dependences based on empirical data. Series in Statistics. Springer, Berlin, New York (1982)"},{"key":"7_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V.N. Vapnik","year":"1995","unstructured":"Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Berlin (1995)"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Widrow, B., Hoff, M.E.: Adaptive switching circuits. In: IRE WESCON Conv. Record, Part 4, pp. 96\u2013104 (1960)","DOI":"10.21236\/AD0241531"},{"key":"7_CR45","volume-title":"Adaptive Signal Processing","author":"B. Widrow","year":"1985","unstructured":"Widrow, B., Stearns, S.D.: Adaptive Signal Processing. Prentice-Hall, Englewood Cliffs (1985)"},{"key":"7_CR46","unstructured":"Wolf, R., Platt, J.: Postal address block location using a convolutional locator network. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol.\u00a06, pp. 745\u2013752 (1994)"}],"container-title":["Lecture Notes in Computer Science","Advanced Lectures on Machine Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-28650-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T16:55:18Z","timestamp":1590684918000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-28650-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540231226","9783540286509"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-28650-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004]]}}}