Modified constrained learning algorithms incorporating additional functional constraints into neural networks

Information Sciences

Volumn 178, Issue 3, 2008, Pages 907-919

  Han, Fei ^a   Ling, Qing Hua ^b   Huang, De Shuang ^c  

^a JIANGSU UNIVERSITY   (China)

^b JIANGSU UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

^c INSTITUTE OF INTELLIGENT MACHINES   (China)

Author keywords

Constrained learning algorithm; Convergence rate; Generalization performance; High frequency components; Mapping sensitivity

Indexed keywords

COMPUTER SIMULATION; CONSTRAINT THEORY; NEURAL NETWORKS; SENSITIVITY ANALYSIS;

ACTIVATION FUNCTIONS; CONSTRAINED LEARNING ALGORITHMS; CONVERGENCE RATE; HIGH FREQUENCY COMPONENTS; MAPPING SENSITIVITY;

LEARNING ALGORITHMS;

EID: 35748930579     PISSN: 00200255     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ins.2007.09.008     Document Type: Article

References (29)

1. Armano G., Marchesi M., and Murru A. A hybrid genetic-neural architecture for stock indexes forecasting. Information Sciences 170 (2005) 3-33
2. Baum E., and Haussler D. What size net gives valid generalization?. Neural Computation 1 (1989) 151-160
3. Bernier J.L., Ortega J., Rojas I., and Prieto A. Improving the tolerance of multilayer perceptrons by minimizing the statistical sensitivity to weight deviations. Neurocomputing 31 (2000) 87-103
4. Bishop C.M. Curvature-driven smoothing: a learning algorithm for feedforward networks. IEEE Transactions on Neural Networks 4 (1993) 882-884
5. Chen Y.J., Huang T.C., and Hwang R.C. An effective learning of neural network by using RFBP learning algorithm. Information Sciences 167 (2004) 77-86
6. Chen Y.H., Yang B., Dong J.W., and Abraham A. Time-series forecasting using flexible neural tree model. Information Sciences 174 (2005) 219-235
7. Choi Y.J., Kim H.K., Baek W.P., and Chang S.H. Hybrid accident simulation methodology using artificial neural networks for nuclear power plants. Information Sciences 160 (2004) 207-224
8. Cottrell M., Girard B., et al. Neural modeling for time series: a statistical stepwise method for weight elimination. IEEE Transactions on Neural Networks 6 (1992) 1355-1364
9. Demsar J. Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research 7 (2006) 1-30
10. Goutte C., and Hansen L.K. Regularization with a pruning prior. Neural Networks 10 (1997) 1053-1059
11. Hammadi N.C., and Ito H. A learning algorithm for fault tolerant feedforward neural networks. IEICE Transactions on Information Systems E80-D 1 (1997) 21-27
12. Huang D.S. A constructive approach for finding arbitrary roots of polynomials by neural networks. IEEE Transactions on Neural Networks 15 (2004) 477-491
13. Huang D.S., and Chi Z. Finding roots of arbitrary high order polynomials based on neural network recursive partitioning method. Science in China Series F: Information Sciences 47 (2004) 232-245
14. Huang D.S., Ip H.H.S., and Chi Z. A neural root finder of polynomials based on root moments. Neural Computation 16 (2004) 1721-1762
15. Huang D.S., Ip H.H.S., Chi Z., and Wong H.S. Dilation method for finding close roots of polynomials based on constrained learning neural networks. Physics Letters A 309 (2003) 443-451
16. Jeong D.-G., and Lee S.-Y. Merging back-propagation and Hebbian learning rules for robust classifications. Neural Networks 9 (1996) 1213-1222
17. Jeong S.Y., and Lee S.Y. Adaptive learning algorithms to incorporate additional functional constraints into neural networks. Neurocomputing 35 (2000) 73-90
18. Karras D.A. An efficient constrained training algorithm for feedforward networks. IEEE Transactions on Neural Networks 6 (1995) 1420-1434
19. Karnin E.D. A simple procedure for pruning back-propagation trained neural networks. IEEE Transactions on Neural Networks 1 (1990) 239-242
20. LeCun Y., Denker J.S., and Solla S.A. Optimal brain damage. Advances in Neural Information Processing Systems vol. 2 (1990), Morgan Kaufmann, San Mateo, CA 598-605
21. Levenberg K. A method for the solution of certain non-linear problems in least squares. Quarterly of Applied Mathematics 2 (1944) 164-168
22. Marquardt D.W. An algorithm for the least-squares estimation of nonlinear parameters. SIAM Journal of Applied Mathematics 11 (1963) 431-441
23. Nowlan S.J., and Hinton G.E. Simplifying neural networks by soft weight sharing. Neural Computation 4 (1992) 473-493
24. Poggio T., and Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science 2 247 (1990) 978-982
25. Williams P.M. Bayesian regularization and pruning using a Laplace prior. Neural Computation 7 (1995) 117-143
26. Waibel A., Hanazawa T., Hinton G., Shikano K., and Lang K. Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, Signal Processing 37 (1989) 328-339
27. A.S. Weigend, D.E. Rumelhart, B.A. Hyberman, Generalization by weight-elimination applied to currency exchange rate prediction, in: Proceedings of International Conference on Neural Network, Seattle, 1991, pp. 837-841.
28. http://www.ngdc.noaa.gov/stp/SOLAR/ftpsunspotnumber.html.
29. http://www-psych.stanford.edu/~andreas/Time-Series/SantaFe.html.