{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:49:29Z","timestamp":1779342569454,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":25,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642352881","type":"print"},{"value":"9783642352898","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"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":[[2012]]},"DOI":"10.1007\/978-3-642-35289-8_5","type":"book-chapter","created":{"date-parts":[[2012,11,14]],"date-time":"2012-11-14T07:03:17Z","timestamp":1352876597000},"page":"53-67","source":"Crossref","is-referenced-by-count":413,"title":["Early Stopping \u2014 But When?"],"prefix":"10.1007","author":[{"given":"Lutz","family":"Prechelt","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","unstructured":"Amari, S., Murata, N., M\u00fcller, K.-R., Finke, M., Yang, H.: Statistical theory of overtraining - is cross-validation effective. In: [23], pp. 176\u2013182 (1996)"},{"issue":"5","key":"5_CR2","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/72.623200","volume":"8","author":"S. Amari","year":"1997","unstructured":"Amari, S., Murata, N., M\u00fcller, K.-R., Finke, M., Yang, H.: Aymptotic statistical theory of overtraining and cross-validation. IEEE Trans. on Neural Networks\u00a08(5), 985\u2013996 (1997)","journal-title":"IEEE Trans. on Neural Networks"},{"key":"5_CR3","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1162\/neco.1991.3.4.589","volume":"3","author":"P. Baldi","year":"1991","unstructured":"Baldi, P., Chauvin, Y.: Temporal evolution of generalization during learning in linear networks. Neural Computation\u00a03, 589\u2013603 (1991)","journal-title":"Neural Computation"},{"key":"5_CR4","volume-title":"Advances in Neural Information Processing Systems 6","year":"1994","unstructured":"Cowan, J.D., Tesauro, G., Alspector, J. (eds.): Advances in Neural Information Processing Systems 6. Morgan Kaufman Publishers Inc., San Mateo (1994)"},{"key":"5_CR5","unstructured":"Le Cun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: [22], pp. 598\u2013605 (1990)"},{"key":"5_CR6","unstructured":"Fahlman, S.E.: An empirical study of learning speed in back-propagation networks. Technical Report CMU-CS-88-162, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA (September 1988)"},{"key":"5_CR7","unstructured":"Fahlman, S.E., Lebiere, C.: The Cascade-Correlation learning architecture. In: [22], pp. 524\u2013532 (1990)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Fiesler, E.: Comparative bibliography of ontogenic neural networks (1994) (submitted for publication)","DOI":"10.1007\/978-1-4471-2097-1_188"},{"key":"5_CR9","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1016\/S0893-6080(05)80122-4","volume":"6","author":"W. Finnoff","year":"1993","unstructured":"Finnoff, W., Hergert, F., Zimmermann, H.G.: Improving model selection by nonconvergent methods. Neural Networks\u00a06, 771\u2013783 (1993)","journal-title":"Neural Networks"},{"key":"5_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S. Geman","year":"1992","unstructured":"Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias\/variance dilemma. Neural Computation\u00a04, 1\u201358 (1992)","journal-title":"Neural Computation"},{"key":"5_CR11","volume-title":"Advances in Neural Information Processing Systems 5","year":"1993","unstructured":"Hanson, S.J., Cowan, J.D., Giles, C.L. (eds.): Advances in Neural Information Processing Systems 5. Morgan Kaufman Publishers Inc., San Mateo (1993)"},{"key":"5_CR12","unstructured":"Hassibi, B., Stork, D.G.: Second order derivatives for network pruning: Optimal brain surgeon. In: [11], pp. 164\u2013171 (1993)"},{"key":"5_CR13","unstructured":"Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: [16], pp. 950\u2013957 (1992)"},{"key":"5_CR14","unstructured":"Levin, A.U., Leen, T.K., Moody, J.E.: Fast pruning using principal components. In: [4] (1994)"},{"key":"5_CR15","volume-title":"Advances in Neural Information Processing Systems 3","year":"1991","unstructured":"Lippmann, R.P., Moody, J.E., Touretzky, D.S. (eds.): Advances in Neural Information Processing Systems 3. Morgan Kaufman Publishers Inc., San Mateo (1991)"},{"key":"5_CR16","volume-title":"Advances in Neural Information Processing Systems 4","year":"1992","unstructured":"Moody, J.E., Hanson, S.J., Lippmann, R.P. (eds.): Advances in Neural Information Processing Systems 4. Morgan Kaufman Publishers Inc., San Mateo (1992)"},{"key":"5_CR17","unstructured":"Morgan, N., Bourlard, H.: Generalization and parameter estimation in feedforward nets: Some experiments. In: [22], pp. 630\u2013637 (1990)"},{"issue":"4","key":"5_CR18","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1162\/neco.1992.4.4.473","volume":"4","author":"S.J. Nowlan","year":"1992","unstructured":"Nowlan, S.J., Hinton, G.E.: Simplifying neural networks by soft weight-sharing. Neural Computation\u00a04(4), 473\u2013493 (1992)","journal-title":"Neural Computation"},{"key":"5_CR19","unstructured":"Prechelt, L.: PROBEN1 \u2014 A set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report 21\/94, Fakult\u00e4t f\u00fcr Informatik, Universit\u00e4t Karlsruhe, Germany, Anonymous, ftp:\/\/pub\/papers\/techreports\/1994\/1994-21.ps.gz on, ftp.ira.uka.de (September 1994)"},{"issue":"5","key":"5_CR20","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/72.248452","volume":"4","author":"R. Reed","year":"1993","unstructured":"Reed, R.: Pruning algorithms \u2014 a survey. IEEE Transactions on Neural Networks\u00a04(5), 740\u2013746 (1993)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: Proc. of the IEEE Intl. Conf. on Neural Networks, San Francisco, CA, pp. 586\u2013591 (April 1993)","DOI":"10.1109\/ICNN.1993.298623"},{"key":"5_CR22","volume-title":"Advances in Neural Information Processing Systems 2","year":"1990","unstructured":"Touretzky, D.S. (ed.): Advances in Neural Information Processing Systems 2. Morgan Kaufman Publishers Inc., San Mateo (1990)"},{"key":"5_CR23","volume-title":"Advances in Neural Information Processing Systems 8","year":"1996","unstructured":"Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.): Advances in Neural Information Processing Systems 8. MIT Press, Cambridge (1996)"},{"key":"5_CR24","unstructured":"Wang, C., Venkatesh, S.S., Judd, J.S.: Optimal stopping and effective machine complexity in learning. In: [4] (1994)"},{"key":"5_CR25","unstructured":"Weigend, A.S., Rumelhart, D.E., Huberman, B.A.: Generalization by weight-elimination with application to forecasting. In: [15], pp. 875\u2013882 (1991)"}],"container-title":["Lecture Notes in Computer Science","Neural Networks: Tricks of the Trade"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35289-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T12:32:29Z","timestamp":1562329949000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35289-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642352881","9783642352898"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35289-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}