Abstract
In this paper we propose a model of neural networks ensemble consisting of a number of MLPs, that deals with an imperfect learning supervisor that occasionally produces incorrect teacher signals. It is known that a conventional unitary neural network will not learn optimally from this kind of supervisor. We consider that the imperfect supervisor generates two kinds of input-output relations, the correct relation and the incorrect one. The learning characteristics of the proposed model allows the ensemble to automatically train one of its members to learn only from the correct input-output relation, producing a neural network that can to some extent tolerate the imperfection of the supervisor.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Sharkey, A.: On Combining Artificial Neural Nets. Connection Science 8(3 & 4) (1996) 299–313
Jacobs, R.A., Jordan, M., Nowlan, S., Hinton, G.: Adaptive Mixture of Local Experts. Neural Computation 3 (1991) 79–87
Jacobs, R.A., Jordan, M.: A Competitive Modular Connectionists Architecture. Advances in Neural Information Processing Systems 3 (1991) 767–773
Nowlan, S., Hiton, G.: Evaluation of Adaptive Mixture of Competing Experts. Advances in Neural Information Processing Systems 3 (1991) 774–780
Jordan, M., Jacobs, R.: Hierarchical Mixture of Experts and the EM Algorithm. Neural Computation 6 (1994) 181–214
Jacobs, R.: Computational Studies of the Development of Functionally Specialized Neural Modules. Trends in Cognitive Sciences 3 (1999) 31–38
Liu, Y., Yao, X.: A Cooperative Ensemble Learning System. Proc. Int. Joint Conference on Neural Networks 1998 (1998) 2202–2207
Liu, Y., Yao, X.: Simultaneous Training of Negatively Correlated Neural Networks in an Ensemble. IEEE Trans. Systems, Man, Cybernetics B 29(6) (1999) 716–725
Sharkey, A., Sharkey, N.: Diversity, Selection, and Ensemble of Artificial Neural Nets. Proc. Neural Network and Their Applications 1997 (1997) 205–212
Baxt, W.: Improving the Accuracy of an Artificial Neural Network Using Multiple Differently Trained Networks. Neural Computation 4 (1992) 772–780
Hansen, L., Salomon, P.: Neural Networks Ensemble. IEEE Trans. Pattern Analysis and Machine Intelligence 12(8) (1990) 993–1001
Rosen, B.: Ensemble Learning Using Decorralated Neural Networks. Connection Science 8(3 & 4) (1996) 373–383
Tumer, K., Gosh, J.: Error Correlation and Error Reduction in Ensemble Classifier. Connection Science 8(3 & 4) (1996) 383–404
Geman, S., Bienenstock, E., Doursat, R.: Neural Networks and the BiasVariance Dillema. Neural Computation 4 (1992) 1–58
Müller, K-R., Kohlmorgen, J., Pawelzik, K.: Segmentation and Identification of Switching Dynamics with Competing Neural Networks. Proc. Int. Conference on Neural Information Processing 1994 (1994) 213–218
Müller, K-R., Kohlmorgen, J., Pawelzik, K.: Analysis of Switcing Dynamics with Competing Neural Networks. IEICE Trans. Fundamentals E78-A(10) (1995) 1306–1314
Pawelzik, K., Kohlmorgen, J., Müller, K-R.: Annealed Competition of Experts for a Segmentation and Classification of Switching Dynamics. Neural Computation 8 (1996) 304–356
Hartono, P., Hashimoto, S.: Ensemble of Neural Network with Temperature Control. Proc. Int. Joint Conference on Neural Networks 1999 (1999) 4073–4078
Hartono, P., Hashimoto, S.: Temperature Switching in Neural Network Ensemble. Journal of Signal Processing 4(5) (2000) 395–402
Rumelhart, D., McClelland, J.: Learning Internal Representation by Error Propagation. Parallel Distributed Processing 1, MIT Press (1996) 318–362
Fisher, R: The Use of Multiple Measurement in Toxanomic Problems. Annals of Eugenic (1936) 179–188
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hartono, P., Hashimoto, S. (2001). Learning-Data Selection Mechanism through Neural Networks Ensemble. In: Kittler, J., Roli, F. (eds) Multiple Classifier Systems. MCS 2001. Lecture Notes in Computer Science, vol 2096. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48219-9_19
Download citation
DOI: https://doi.org/10.1007/3-540-48219-9_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42284-6
Online ISBN: 978-3-540-48219-2
eBook Packages: Springer Book Archive