Abstract
This paper presents the generalization capability of multilayer perceptrons (MLP). The learning algorithm is based on mixing the concepts of dynamic tunneling along with error backpropagation (EBPDT), which enables detrapping of the local minimum point. In this study, the generalization capability is presented on three standard datasets, and the k-fold cross validation results is presented for two of the datasets. A comparative study of the performance of the proposed method with EBP clearly demonstrates the power of tunneling applied in conjunction with EBP type of learning.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Haykin, S.: Neural Networks: A Comprehensive Foundation. 2nd edn. Prentice Hall, New Jersey (1999)
RoyChowdhury, P., Singh, Y.P., Chansarkar, R.A.: Dynamic Tunneling Technique for Efficient Training of Multilayer Perceptrons. IEEE Trans. On Neural Networks. 10 (1999) 48–55
Barhen, J., Protopopescu, V., Reister, D.: TRUST: A Deterministic Algorithm for Global Optimization. Science. 276 (1997) 1094–1097
RoyChowdhury, P., Singh, Y.P., Chansarkar, R.A.: Hybridization of Gradient Descent Algorithms with Dynamic Tunneling Methods for Global Optimization. IEEE Trans. On Systems, Man, and Cybernetics, Part A. 30 (2000) 386–392
Spiegel, M.R.: Theory and Problems of Statistics. 1st edn. McGraw-Hill, Singapore (1981)
Singh, Y.P., RoyChowdhury, P.: Dynamic tunneling based regularization in feedforward neural networks. Artifical Intelligence. 131 (2001) 55–71
Chien, Y.-t.: Interactive Pattern Recognition (Electrical Engineering and Electronics; v.3). Marcel Dekker Inc., New York (1978)
Murphy, P., Aha, D.: Repository of Machine Learning Databases. Dept. Inform. Comput. Sci.
Joshi, A., Ramakrishnan, N., Houstis, E.N., Rice, J.R.: On neurobiological, neuro-fuzzy, machine learning, and statistical pattern recognition techniques. IEEE Trans. On Neural Networks. 8 (1997) 18–31
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chowdhury, P.R., Shukla, K.K. (2002). On Generalization and K-Fold Cross Validation Performance of MLP Trained with EBPDT. In: Pal, N.R., Sugeno, M. (eds) Advances in Soft Computing — AFSS 2002. AFSS 2002. Lecture Notes in Computer Science(), vol 2275. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45631-7_47
Download citation
DOI: https://doi.org/10.1007/3-540-45631-7_47
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43150-3
Online ISBN: 978-3-540-45631-5
eBook Packages: Springer Book Archive