On Combining Artificial Neural Nets

Connection Science

Volumn 8, Issue 3-4, 1996, Pages 299-314

  Sharkey, Amanda J C ^a  

^a UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

Artificial neural networks; Ensembles; Modularity

Indexed keywords

EID: 0030372023     PISSN: 09540091     EISSN: None     Source Type: Journal    
DOI: 10.1080/095400996116785     Document Type: Article

References (46)

1. Al-Ghoneim, K. & Vijaya Kumar, B.V.K. (1995) Learning ranks with neural networks (invited paper). In Applications and Science of Artificial Neural Networks, Proceedings of the SPIE, Vol. 2492, pp. 446-464.
2. Barnett, J.A. (1981) Computational methods for a mathematical theory of evidence. In Proceedings of IJCAI, pp. 868-875.
3. Bishop, C. (1995) Neural Networks for Pattern Recognition. Oxford: Clarendon Press.
4. Breiman, L. (1993) Stacked Regression. Technical Report, University of California, Berkeley.
5. Breiman, L. (1996a) Bias, Variance and Arcing Classifiers. Technical Report 460, University of California, Berkeley.
6. Breiman, L. (1996b) Bagging predictors. Machine Learning, 24, 123-140.
7. Clemen, R. (1989) Combining forecasts: a review and annotated bibliography. International Journal of Forecasting, 5, 559-583.
8. Denker, J., Schwartz, D., Wittner, B., Solla, S., Howard, R., Jackel, L. & Hopfield, J. (1987) Large automatic learning, rule extraction and generalisation. Complex Systems, 1, 877-922.
9. Drucker, H., Cortes, C., Jackel, L.D., LeCun, Y. & Vapnik, V. (1994) Boosting and other ensemble methods. Neural Computation, 6, 1289-1301.
10. Eckhardt, D.E. & Lee, L.D. (1985) A theoretical basis for the analysis of multiversion software subject to coincident errors. IEEE Transactions on Software Engineering, SE-11, 12, 1511-1517.
11. Fodor, J.A. (1983) The Modularity of Mind: An essay on Faculty Psychology. London: A Bradford Book, MIT Press.
12. Freund, Y. & Schapire, R. (1996) Experiments with a new boosting algorithm. In Machine Learning: Proceedings of the Thirteenth International Conference.
13. Geman, S., Bienenstock, E. & Doursat, R. (1992) Neural networks and the bias/variance dilemma. Neural Computation, 4, 41-58.
14. Genest, C. & Zidek, J.V. (1986) Combining probability distributions: a critique and annotated bibliography. Statistical Science, 1, 114-148.
15. Granger, C.W.J. (1989) Combining forecasts - twenty years later. Journal of Forecasting, 8, 167-173.
16. Gueard, J.B. Jr & Clemen, R.T. (1989) Collinearity and the use of latent root regression for combining GNP forecasts. Journal of Forecasting, 8, 231-238.
17. Hampshire, J. & Waibel, A. (1989) The Meta-Pi Network: Building Distributed Knowledge Systems for Robust Pattern Recognition. Technical Report CMU-CS-89-166, Carnegie Mellon University, Pittsburgh, PA.
18. Hansen, L.K. & Salamon, P. (1990) Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 993-1000.
19. Hashem, S. & Schmeiser, B. (1993) Approximating a function and its derivatives using MSE-optimal linear combinations of trained feedforward neural networks. In Proceedings of the World Congress on Neural Networks, Vol. 1. New Jersey: Lawrence Erlbaum Associates, pp. 617-620.
20. Jacobs, R.A. (1995) Methods for combining experts' probability assessments. Neural Computation, 7, 867-888.
21. Jacobs, R.A. (1996) Bias/variance analyses of mixtures-of-experts architectures. Neural Computation, 9.
22. Jacobs, R.A., Jordan, M.I., Nowlan, S.J. & Hinton, G.E. (1991) Adaptive mixtures of local experts. Neural Computation, 3, 79-97.
23. Jordan, M.I. & Jacobs, R.A. (1994) Hierarchical mixtures of experts and the EM algorithm. Neural Computation, 6, 181-214.
24. Jordan, M.I. & Jacobs, R.A. (1995) Modular and Hierarchical Learning Systems. In M.A. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks. Bradford Books/MIT Press, pp. 579-581.
25. Kim, K. & Bartlett, E.B. (1995) Error estimation by series association for neural network systems. Neural Computation, 7, 799-808.
26. Knight, J.C. & Leveson, N.G. (1986) An experimental evaluation of independence in multiversion programming. Transactions on Software Engineering, SE-12, 96-109.
27. Kolen, J.F. & Pollack, J.B. (1990) Backpropagation Is Sensitive to Initial Conditions. Technical Report TR 90-JK-BPSIC, Computer and Information Science Department, Ohio State University.
28. Krogh, A. & Vedelsby, J. (1995) Neural network ensembles, cross validation and active learning. In G. Tesauro, D.S. Touretzky & T.K. Leen (Eds), Advances in Neural Information Processing Systems, 7. Cambridge, MA: MIT Press, pp. 231-238.
29. LeBlanc, M. & Tibshirani, R. (1993) Combining estimates in regression and classification. Paper available from ftp site: ustat.toronto.edu.
30. Littlewood, B. & Miller, D.R. (1989) Conceptual modelling of coincident failures in multiversion software. IEEE Transactions on Software Engineering, 15, pp. 1596-1614.
31. Nilsson, N.J. (1965) Learning Machines: Foundations of Trainable Pattern-Classifying Systems. NY: McGraw Hill.
32. Peng, F., Jacobs, R.A. & Tanner, M.A. (1996) Bayesian inference in mixtures-of-experts and hierarchical mixtures-of-experts models with an application to speech recognition. Journal of the American Statistical Association (in press).
33. Perrone, M. & Cooper, L.N. (1993) When networks disagree: Ensemble methods for hybrid neural networks. In R.J. Mammone (Ed.), Neural Networks for Speech and Image Processing. London: Chapman and Hall.
34. Rogova, G. (1994) Combining the results of several neural network classifiers. Neural Networks, 7, 777-781.
35. Rumelhart, D.E. & McClelland, J.L. (1986) On learning the past tense of English verbs. In D.E. Rumelhart, J.L. McClelland & PDP Research Group (Eds), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, MA: MIT Press.
36. Schapire, R.E. (1990) The strength of weak learnability. Machine Learning, 5, 197-227.
37. Sharkey, A.J.C. & Sharkey, N.E. (1995a) How to Improve the Reliability of Artificial Neural Networks. Research Report CS-95-11, Department of Computer Science, University of Sheffield.
38. Sharkey, N.E. & Sharkey, A.J.C. (1995b) An Analysis of castrophic interference. Connection Science, 7, 313-341.
39. Sharkey, A.J.C., Sharkey, N.B. & Chandroth, G.O. (1995a) Neural nets and diversity. In Proceedings of the 14th International Conference on Computer Safety, Reliability and Security, Belgirate, Italy, pp. 375-389.
40. Sharkey, A.J.C. Sharkey, N.E. & Chandroth, G.O. (1995b) Diverse Neural Net Solutions to a Fault Diagnosis Problem. Research Report CS-95-10, Department of Computer Science, University of Sheffield. Neural Computing and Applications (in press).
41. Sharkey, N.E., Neary, J. & Sharkey, A.J.C. (1995c) Searching weight space for backpropagation solution types. In L.F. Niklasson & M.B. Boden (Eds), Current Trends in Connectionism. Hillsdale, NJ: Lawrence Erlbaum Associates, pp. 103-121.
42. Tumer, K. & Ghosh, J. (1995) Theoretical Foundations of Linear and Order Statistics Combiners for Neural Pattern Classifiers. Technical Report TR-95-02-98, The Computer and Vision Research Center, University of Texas, Austin. (Available from http://www.lans.ece.utexas.edu under select publications-tech reports.)
43. Tumer, K. & Ghosh, J. (1996) Analysis of decision boundaries in linearly combined neural classifiers. Pattern Recognition, 29, 341-348.
44. Waibel, A., Sawai, H. & Shikano, K. (1989) Modularity and scaling in large phonemic neural networks. IEEE Transactions on Acoustics, Speech and Signal Processing, 37, 1888-1898.
45. Wolpert, D.H. (1992) Stacked generalization. Neural Networks, 5, 241-259.
46. Xu, L., Krzyzak, A. & Suen, C.Y. (1992) Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Transctions on Systems, Man, Cybernetics, 22, 418-435.