The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Neural networks for classification: a survey
Abstract
Classification is one of the most active research and application areas of neural networks. The literature is vast and growing. This paper summarizes some of the most important developments in neural network classification research. Specifically, the issues of posterior probability estimation, the link between neural and conventional classifiers, learning and generalization tradeoff in classification, the feature variable selection, as well as the effect of misclassification costs are examined. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Wolpert, D. H. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80023-1 · Cited by 7,951
Hansen, L. K., & Salamon, P. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.58871 · Cited by 4,260
Neural Networks and the Bias/Variance Dilemma
Geman, S., Bienenstock, E., & Doursat, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.1 · Cited by 3,578 · cited 3×
“The work by Geman et al. [57] on bias and variance tradeoff under the quadratic objective function has stimulated a lot of research interest and activities in the neural network, machine learning, and statistical communities.”
BackgroundMethodInfluentialA practical Bayesian framework for backpropagation networks
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.448 · Cited by 2,917
Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis
Zhang, G., Y. Hu, M., Eddy Patuwo, B., & C. Indro, D. (1999) · European Journal of Operational Research · doi:10.1016/s0377-2217(98)00051-4 · Cited by 677
Self-citation
Research works printed but not linked: 187
- 10.1109/TIT.1974.1055260 · DOI · Paper page
- 10.1080/095400996116839 · DOI · Paper page
- 10.1016/0031-3203(95)00085-2 · DOI · Paper page
- 10.1109/AIAWS.1991.236576 · DOI
- 10.1109/IJCNN.1998.682376 · doi:10.1109/ijcnn.1998.682376
- 10.1016/0167-9473(95)00033-X · DOI
- 10.1080/09540098908915648 · DOI · Paper page
- 10.1109/72.80269 · DOI · Paper page
- 10.1111/j.1540-5915.1999.tb00902.x · DOI
- tibshirani, 1996, Bias variance and prediction error for classification rules
- 10.1109/72.728352 · DOI · Paper page
- 10.1145/212094.212114 · DOI · Paper page
- devijver, 1982, Pattern Recognition a Statistical Approach
- 10.1080/03610929708831963 · doi:10.1080/03610929708831963
- 10.1214/ss/1177010638 · DOI · Paper page
- 10.1002/(SICI)1097-0142(19970215)79:4<857::AID-CNCR24>3.0.CO;2-Y · DOI · Paper page
- 10.1002/ssu.2980100111 · DOI
- 10.1038/sj/jors/0450408 · DOI
- 10.1109/72.728388 · doi:10.1109/72.728388
- 10.1016/0925-2312(95)00121-2 · DOI
- 10.1016/0893-6080(90)90019-H · DOI
- 10.1016/0893-6080(94)90023-X · DOI
- 10.1162/neco.1989.1.4.425 · DOI · Paper page
- weiss, 1991, Computer Systems That Learn
- weigend, 1994, on overfitting and the effective number of hidden units, Proc of the 1988 Connectionist Models Summer School, 335
- 10.1142/S0129065790000102 · DOI · Paper page
- wolpert, 1992, on the connection between in-sample testing and generalization error, Complex Syst, 6, 47
- 10.1016/0167-9236(94)90024-8 · DOI · Paper page
- 10.1145/175247.175257 · DOI · Paper page
- 10.1016/0031-3203(93)90060-A · DOI
- 10.1214/aos/1024691079 · DOI · Paper page
- 10.1287/mnsc.41.3.555 · DOI
- 10.1109/72.286919 · DOI
- 10.7326/0003-4819-115-11-843 · DOI · Paper page
- 10.1016/0925-2312(94)E0053-T · DOI
- 10.1162/neco.1992.4.5.772 · DOI
- 10.1109/72.623216 · DOI · Paper page
- 10.1109/72.286885 · DOI
- 10.1016/S0893-6080(98)00043-4 · DOI
- 10.1109/34.31448 · DOI · Paper page
- 10.1017/S0269888997003123 · DOI · Paper page
- sharkey, 1999, multi-net systems, Combining Artificial Neural Nets Ensemble and Modular Multi-Net Systems, 1
- 10.1109/72.80304 · DOI
- 10.1007/BF00114160 · DOI · Paper page
- sen, 1995, predicting corporate mergers, Proceedings of the Neural Networks in the Capital Markets Conference, 325
- 10.1109/72.572104 · DOI · Paper page
- 10.1109/IJCNN.1990.137825 · doi:10.1109/ijcnn.1990.137825
- 10.1016/0169-7439(94)00086-X · doi:10.1016/0169-7439(94)00086-x
- 10.1016/0893-6080(89)90044-0 · DOI · Paper page
- 10.1016/S0893-6080(96)00086-X · DOI
- 10.1016/0167-9473(95)00032-1 · DOI · Paper page
- 10.1016/0031-3203(78)90029-8 · DOI
- 10.1109/ICASSP.1990.115636 · DOI
- 10.1142/S0129065797000227 · DOI
- garson, 1991, interpreting neural network connection weights, AI Expert, 47
- 10.1016/0893-6080(91)90071-C · DOI
- 10.1016/S0893-6080(97)00120-2 · doi:10.1016/s0893-6080(97)00120-2
- funahashi, 1990, Introduction to statistical pattern recognition
- dietterich, 1995, solving multiclass learning problems via error-correcting output codes, J Artif Intell Res, 2, 263, 10.1613/jair.105 · DOI · Paper page
- 10.1287/mnsc.38.7.926 · DOI · Paper page
- 10.1016/0893-6080(95)00051-8 · DOI
- 10.1103/PhysRevE.48.1497 · doi:10.1103/physreve.48.1497
- 10.1117/12.59918 · DOI · Paper page
- 10.1109/IJCNN.1990.137709 · DOI
- 10.1016/S0957-4174(98)00041-4 · DOI · Paper page
- 10.1016/0305-0548(93)90063-O · DOI
- 10.1109/72.508942 · DOI
- 10.1016/S0893-6080(98)00117-8 · DOI · Paper page
- 10.1016/0893-6080(94)90026-4 · DOI
- 10.1109/IJCNN.1990.137847 · doi:10.1109/ijcnn.1990.137847
- 10.1109/21.108291 · doi:10.1109/21.108291
- 10.1162/089976699300016737 · DOI
- 10.1016/0925-2312(95)00100-X · doi:10.1016/0925-2312(95)00100-x
- atlas, 1990, performance comparisons between backpropagation networks and classification trees on three real-world applications, Advances in neural information processing systems, 2, 622
- 10.1016/0031-3203(90)90008-9 · doi:10.1016/0031-3203(90)90008-9
- 10.1016/0893-6080(91)90033-2 · DOI · Paper page
- 10.1016/S0898-1221(97)00059-X · DOI
- 10.1142/9789812816955_0048 · doi:10.1142/9789812816955_0048
- 10.1016/S0893-6080(98)00031-8 · doi:10.1016/s0893-6080(98)00031-8
- 10.1007/978-1-4899-4541-9 · DOI · Paper page
- 10.1023/A:1009778005914 · DOI · Paper page
- flexer, 1996, statistical evaluation of neural network experiments: minimum requirements and current practice, Proc 13th Eur Meeting Cybernetics Systems Research, 1005
- duda, 1973, Pattern Classification and Scene Analysis
- dietterich, 1995, Machine learning bias statistical bias and statistical variance of decision tree algorithms
- 10.1109/ICNN.1988.23958 · DOI · Paper page
- 10.1016/0167-8655(95)00113-1 · DOI
- ho, 1994, decision combination in multiple classifier systems, IEEE Trans on Pattern Anal Machine Intell, 16, 66, 10.1109/34.273716 · DOI · Paper page
- 10.1016/S0893-6080(98)00093-8 · doi:10.1016/s0893-6080(98)00093-8
- 10.1162/089976698300017232 · DOI
- hertz, 1991, Introduction to the Theory of Neural Computation
- 10.1023/A:1022631118932 · DOI · Paper page
- 10.1073/pnas.84.23.8429 · DOI · Paper page
- 10.1109/72.554187 · DOI
- 10.1049/el:19901270 · DOI
- 10.1016/0893-6080(91)90009-T · DOI · Paper page
- 10.1016/0957-4174(95)00032-1 · doi:10.1016/0957-4174(95)00032-1
- 10.1109/72.329697 · DOI · Paper page
- 10.1142/S021800149100020X · doi:10.1142/s021800149100020x
- hampshire, 1990, equivalence proofs for multilayer perceptron classifiers and the bayesian discriminant function, Proc 1990 Connectionist Models Summer School
- harreli, 1985, a comparison of the discriminant analysis and logistic regression under multivariate normality, Biostatistics Statistics in Biomedical Public Health and Environmental Sciences
- 10.2307/2583712 · doi:10.2307/2583712
- 10.1109/72.377990 · DOI · Paper page
- 10.1016/S0893-6080(96)00098-6 · DOI · Paper page
- hashem, 1999, treating harmful collinearity in neural network ensembles, Combining Artificial Neural Nets Ensemble and Modular Multi-Net Systems, 101
- 10.1038/sj/jors/0440106 · doi:10.1038/sj/jors/0440106
- 10.1109/72.661122 · DOI
- 10.1109/72.165591 · DOI · Paper page
- krogh, 1995, neural network ensembles, cross validation, and active learning, Adv Neural Inform Process, 7, 231
- 10.1162/neco.1997.9.6.1211 · DOI
- 10.1016/B978-1-55860-377-6.50046-3 · DOI · Paper page
- kohavi, 1996, bias plus variance decomposition for zero-one loss functions, Proc 13th Int Conf Machine Learning, 275
- 10.1142/S0129065792000218 · doi:10.1142/s0129065792000218
- 10.1109/72.165597 · DOI · Paper page
- 10.1109/21.155943 · DOI · Paper page
- 10.1080/03610928208828251 · DOI
- 10.1109/34.667881 · DOI · Paper page
- le cun, 1990, handwritten digit recognition with a back-propagation network, Adv Neural Inform Process Syst, 2, 396
- le cun, 1990, optimal brain damage, Advances in neural information processing systems, 2, 598
- 10.1016/0377-2217(93)E0274-2 · DOI
- 10.1142/9789812816955_0005 · doi:10.1142/9789812816955_0005
- huang, 1987, comparisons between neural net and conventional classifiers, IEEE 1st Int Conf Neural Networks, 485
- hu, 1996, using neural networks to predict performance of sino-foreign joint ventures, Int J Comput Intell Organ, 1, 134
- 10.1162/neco.1995.7.5.867 · DOI · Paper page
- hung, 1996, estimating posterior probabilities in classification problems with neural networks, Int J Comput Intell Organ, 1, 49
- 10.1109/IJCNN.1990.137550 · DOI
- 10.1016/0893-6080(94)00098-7 · DOI · Paper page
- 10.1162/neco.1997.9.2.369 · DOI
- james, 1997, Generalizations of the bias/variance decomposition for prediction error
- 10.1109/72.554189 · DOI · Paper page
- 10.1109/72.88169 · doi:10.1109/72.88169
- 10.1016/0925-2312(94)00060-3 · DOI
- lee, 1991, bayesian and neural-network pattern recognition: a theoretical connection and empirical results with handwritten characters, Artificial Neural Networks and Statistical Pattern Recognition, 89
- 10.1111/j.1540-5915.1993.tb00491.x · DOI · Paper page
- papoulix, 1965, Probability random variables and stochastic processes
- 10.1142/S0129065789000475 · DOI · Paper page
- 10.1109/72.238319 · doi:10.1109/72.238319
- perrone, 1993, when networks disagree: ensemble methods for hybrid neural networks, Int Symp Speech Image Processing and Neural Networks, 126
- perrone, 1994, putting it all together: methods for combining neural networks, Advances in neural information processing systems, 6, 1188
- 10.1142/9789812816955_0012 · doi:10.1142/9789812816955_0012
- qi, 1995, option pricing using ann: the case of s&p 500 index call options, Proc 3rd Int Conf Neural Networks Capital Markets, 78
- 10.1016/S0893-6080(97)00135-4 · DOI
- 10.1016/0893-6080(95)00123-9 · DOI
- 10.1080/01621459.1978.10480080 · DOI · Paper page
- 10.1109/34.75512 · DOI · Paper page
- 10.1016/S0893-6080(97)00136-6 · DOI
- 10.1162/neco.1991.3.4.461 · DOI · Paper page
- 10.1109/72.248452 · DOI · Paper page
- 10.1007/978-1-4899-3099-6_2 · DOI · Paper page
- ripley, 1994, neural networks and related methods for classification, J R Statist Soc B, 56, 409
- 10.1016/0893-6080(94)90099-X · DOI · Paper page
- 10.1016/S0893-6080(05)80057-7 · DOI
- 10.1109/72.80266 · DOI · Paper page
- rumelhart, 1995, backpropagation: the basic theory, Backpropagation Theory Architectures and Applications, 1
- 10.1016/0378-4266(94)90007-8 · DOI · Paper page
- al-ghoneim, 1995, learning ranks with neural networks, Proc SPIE Applications Science Artificial Neural Networks, 2492, 446, 10.1117/12.205150 · doi:10.1117/12.205150
- 10.1023/A:1009752403260 · DOI · Paper page
- 10.1162/neco.1992.4.3.415 · DOI · Paper page
- 10.1109/34.88570 · doi:10.1109/34.88570
- 10.1088/0954-898X/1/3/002 · doi:10.1088/0954-898x/1/3/002
- 10.1162/neco.1989.1.1.1 · DOI · Paper page
- 10.1109/35.41401 · DOI · Paper page
- lim, 1998, An empirical comparison of decision trees and other classification methods
- 10.1016/0167-8655(92)90029-Y · DOI
- 10.1162/neco.1994.6.5.1005 · DOI · Paper page
- 10.1162/neco.1991.3.4.484 · DOI
- 10.1111/j.1540-5915.1995.tb01427.x · DOI
- 10.1109/72.392248 · DOI · Paper page
- barlett, 1992, nuclear power plant status diagnostics using artificial neural networks, Nucl Technol, 97, 272, 10.13182/NT92-A34635 · doi:10.13182/nt92-a34635
- 10.1109/72.125864 · DOI · Paper page
- 10.1109/72.248457 · DOI
- 10.1109/CDC.1989.70117 · DOI
- 10.1162/neco.1992.4.2.141 · DOI · Paper page
- 10.1109/72.298224 · DOI · Paper page
- morgan, 1990, generalization and parameter estimation in feedforward nets: some experiments, Adv Neural Inform Process Syst, 2, 630
- moody, 1995, architecture selection strategies for neural networks: application to corporate bond rating prediction, Proceedings of the Neural Networks in the Capital Markets Conference, 277
- 10.1016/0893-6080(94)90046-9 · DOI · Paper page
- 10.1162/neco.1989.1.1.151 · DOI · Paper page
- mozer, 1989, skeletonization: a technique for trimming the fat from a network via relevance assessment, Advances in neural information processing systems, 1, 107
- 10.1162/neco.1990.2.4.480 · DOI
- 10.1109/5326.725342 · doi:10.1109/5326.725342
- 10.1162/neco.1991.3.2.258 · DOI
- 10.1109/72.134293 · doi:10.1109/72.134293
- michie, 1994, Machine Learning Neural and Statistical Classification
- 10.1162/089976698300017737 · DOI
- murata, 1993, learning curves, model selection and complexity of neural networks, Advances in Neural Information Processing Systems 5, 607
- 10.1109/72.329683 · DOI · Paper page
- 10.1016/S0305-0548(96)00088-3 · DOI
Cited by
Machine learning: a review of classification and combining techniques
Kotsiantis, S. B., Zaharakis, I. D., & Pintelas, P. E. (2006) · Artificial Intelligence Review · doi:10.1007/s10462-007-9052-3 · Cited by 1,582
Wang, T., Shao, W., Huang, Z., Tang, H., Zhang, J., Ding, Z., & Huang, K. (2021) · Nature Communications · doi:10.1038/s41467-021-23774-w · Cited by 671
A survey towards an integration of big data analytics to big insights for value-creation
Saggi, M. K., & Jain, S. (2018) · Information Processing & Management · doi:10.1016/j.ipm.2018.01.010 · Cited by 494
Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain
Althnian, A., AlSaeed, D., Al-Baity, H., Samha, A., Dris, A. B., Alzakari, N., Abou Elwafa, A., & Kurdi, H. (2021) · Applied Sciences · doi:10.3390/app11020796 · Cited by 410
(2019) · NORA - Norwegian Open Research Archives · Cited by 291
Metadata
- Authors
- Zhang, G. P.
- Venue
- IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)
- Published
- 2000
- Volume
- 30
- Issue
- 4
- Pages
- 451-462
- ISSN
- 1094-6977 (ISSN-L)
- OpenAlex
- W2133218851
- Cited by
- 1,667
- References
- 9
- FWCI
- 8.75
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Neural networks for classification: a survey. https://app.cochat.ai/papers/10.1109/5326.897072
- The paper
- Zhang, G. P. (2000). Neural networks for classification: a survey. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews). https://doi.org/10.1109/5326.897072
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.