{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T10:59:14Z","timestamp":1678100354871},"reference-count":41,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2001,10,1]],"date-time":"2001-10-01T00:00:00Z","timestamp":1001894400000},"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":[[2001,10]]},"DOI":"10.1016\/s0893-6080(01)00061-2","type":"journal-article","created":{"date-parts":[[2002,10,14]],"date-time":"2002-10-14T18:58:33Z","timestamp":1034621913000},"page":"1035-1048","source":"Crossref","is-referenced-by-count":8,"title":["An approach to guaranteeing generalisation in neural networks"],"prefix":"10.1016","volume":"14","author":[{"given":"J.Gary","family":"Polhill","sequence":"first","affiliation":[]},{"given":"Michael K.","family":"Weir","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0893-6080(01)00061-2_BIB1","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1162\/neco.1989.1.3.312","article-title":"The Vapnik\u2013Chervonenkis dimension: Information versus complexity in learning","volume":"1","author":"Abu-Mostafa","year":"1989","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB2","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1162\/neco.1989.1.1.151","article-title":"What size net gives valid generalization?","volume":"1","author":"Baum","year":"1989","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB3","series-title":"Neural networks for pattern recognition","author":"Bishop","year":"1995"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB4","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1162\/089976699300016557","article-title":"No free lunch for early stopping","volume":"11","author":"Cataltepe","year":"1999","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB5","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1214\/ss\/1177010638","article-title":"Neural networks: A review from a statistical perspective","volume":"9","author":"Cheng","year":"1994","journal-title":"Statistical Science"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB6","first-page":"877","article-title":"Large automatic learning, rule extraction, and generalization","volume":"1","author":"Denker","year":"1987","journal-title":"Complex Systems"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB7","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","article-title":"On the approximate realization of continuous mappings by neural networks","volume":"2","author":"Funahashi","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","article-title":"Neural networks and the bias\/variance dilemma","volume":"4","author":"Geman","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB9","unstructured":"Gibbs, P., & Hiroshi, S. (1997). What is Occam's razor? In: Physics FAQ. http:\/\/www.weburbia.com\/physics\/occam.html."},{"key":"10.1016\/S0893-6080(01)00061-2_BIB10","doi-asserted-by":"crossref","first-page":"2459","DOI":"10.1143\/JJAP.31.2459","article-title":"Learning generalization by validation set","volume":"31","author":"Hasegawa","year":"1992","journal-title":"Japanese Journal of Applied Physics"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB11","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF00993163","article-title":"Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension","volume":"14","author":"Haussler","year":"1994","journal-title":"Machine Learning"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB12","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(01)00061-2_BIB13","first-page":"4198","article-title":"Neural network pruning by fusing hidden layer units","volume":"E74","author":"Kameyama","year":"1991","journal-title":"IEICE Transactions"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB14","series-title":"Advances in neural information processing systems 8","first-page":"183","article-title":"A bound on the error of cross validation using the approximation and estimation rates, with consequences for the training-test split","author":"Kearns","year":"1996"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB15","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1162\/089976699300016304","article-title":"Algorithmic stability and sanity-check bounds for leave-one-out cross-validation","volume":"11","author":"Kearns","year":"1999","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB16","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1009607527399","article-title":"A new method to increase the margin of multilayer perceptrons","volume":"11","author":"Lemaire","year":"2000","journal-title":"Neural Processing Letters"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB17","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MASSP.1987.1165576","article-title":"An introduction to computing with neural nets","volume":"4","author":"Lippmann","year":"1987","journal-title":"IEEE ASSP Magazine"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB18","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian interpolation","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB19","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","article-title":"A practical Bayesian framework for backpropagation networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB20","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1162\/neco.1992.4.5.720","article-title":"The evidence framework applied to classification networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB21","unstructured":"McClelland, J.L., Rumelhart, D. E., & Hinton, G. E. (1986). The appeal of parallel distributed processing. In D. E. Rumelhart, J. L. McClelland and The PDP Research Group (Eds.), Parallel distributed processing volume I: Foundations (pp. 3\u201344). Cambridge, MA: MIT Press."},{"key":"10.1016\/S0893-6080(01)00061-2_BIB22","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1007\/BF01413859","article-title":"Estimating MLP generalisation ability without a test set using fast, approximate leave-one-out cross-validation","volume":"5","author":"Myles","year":"1997","journal-title":"Neural Computing & Applications"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB23","series-title":"Bayesian learning for neural networks. Lecture notes in statistics 118","author":"Neal","year":"1996"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB24","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1162\/neco.1992.4.4.473","article-title":"Simplifying neural networks by soft weight-sharing","volume":"4","author":"Nowlan","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB25","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1126\/science.263.5147.641","article-title":"Verification, validation, and confirmation of numerical models in the earth sciences","volume":"263","author":"Oreskes","year":"1994","journal-title":"Science"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB26","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1103\/PhysRevLett.66.2677","article-title":"Generalization performance of Bayes optimal classification algorithm for learning a perceptron","volume":"66","author":"Opper","year":"1991","journal-title":"Physical Review Letters"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB27","series-title":"Guaranteeing generalisation in neural networks. Ph. D. Thesis","author":"Polhill","year":"1996"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB28","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/S0893-6080(98)00010-0","article-title":"Automatic early stopping using cross validation: Quantifying the criteria","volume":"11","author":"Prechelt","year":"1998","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB29","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/S0893-6080(96)00086-X","article-title":"Two strategies to avoid overfitting in feedforward neural networks","volume":"10","author":"Schittenkopf","year":"1997","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB30","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/S0893-6080(96)00127-X","article-title":"Discovering neural nets with low Kolmogorov complexity and high generalization capability","volume":"10","author":"Schmidhuber","year":"1997","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB31","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1162\/neco.1990.2.3.374","article-title":"Exhaustive learning","volume":"2","author":"Schwartz","year":"1990","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB32","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0893-6080(91)90033-2","article-title":"Creating artificial neural networks that generalize","volume":"4","author":"Sietsma","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB33","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/BF01189880","article-title":"Neural network constructive algorithms: Trading generalization for learning efficiency?","volume":"12","author":"Smieja","year":"1993","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB34","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/0167-8191(90)90080-S","article-title":"The geometry of multi-layer perceptron solutions","volume":"14","author":"Smieja","year":"1990","journal-title":"Parallel Computing"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB35","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/S0893-6080(05)80037-1","article-title":"Uniqueness of the weights for minimal feedforward nets with a given input\u2013output map","volume":"5","author":"Sussmann","year":"1992","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB36","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1093\/mind\/XXVII.3.345","article-title":"The myth of Occam's razor","volume":"27","author":"Thorburn","year":"1918","journal-title":"Mind"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB37","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1080\/09528139408953794","article-title":"A theory of cross-validation error","volume":"6","author":"Turney","year":"1994","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB38","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1137\/1116025","article-title":"On the uniform convergence of relative frequencies of events to their probabilities","volume":"16","author":"Vapnik","year":"1971","journal-title":"Theory of Probability and its Applications"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB39","series-title":"Proceedings of the 1990 Connectionist Models Summer School","first-page":"105","article-title":"Back-propagation, weight-elimination, and time series prediction","author":"Weigend","year":"1991"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB40","doi-asserted-by":"crossref","unstructured":"Weir, M. K., & Polhill, J. G. (1994). Bidirectional convergence: A cognitive approach to generalisation. In Proceedings of the IEEE International Conference on Neural Networks, Orlando, Florida. (Vol. IV, pp. 2285\u20132290).","DOI":"10.1109\/ICNN.1994.374575"},{"key":"10.1016\/S0893-6080(01)00061-2_BIB41","series-title":"Brain processes, theories and models: An International Conference in honour of W.S. McCulloch 25 years after his death","first-page":"204","article-title":"Neural bidirectional convergence: A method for concept learning in neural networks and symbolic AI","author":"Weir","year":"1996"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608001000612?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608001000612?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,25]],"date-time":"2019-04-25T11:53:15Z","timestamp":1556193195000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608001000612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,10]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2001,10]]}},"alternative-id":["S0893608001000612"],"URL":"https:\/\/doi.org\/10.1016\/s0893-6080(01)00061-2","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2001,10]]}}}