A novel algorithm for designing three layered artificial neural networks

International Journal of Soft Computing

Volumn 2, Issue 3, 2007, Pages 450-458

  Ahmmed, Suman ^a   Abdullah Al Mamun, Khondaker ^b   Islam, Monirul ^c  

^a UNITED INTERNATIONAL UNIVERSITY   (Bangladesh)

^b UNIVERSITY OF DHAKA   (Bangladesh)

^c BANGLADESH UNIVERSITY OF ENGINEERING AND TECHNOLOGY   (Bangladesh)

Author keywords

ANN; Back propagation; Correlations; Ensemble of ANNs; Generalization; Overfitting

Indexed keywords

EID: 51549113917     PISSN: 18169503     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (27)

1. Ash, T., 1989. ADynamic neuron creation in back-propagation networks. Connection Sci., 1: 365-375.
2. Chauvin, Y., 1990. A Generalization performance of over trained back propagation networks. Neural Networks, Proc. of the EUROSIP Workshop. Almedia, L.B. and C.J. Wellekens (Eds.), pp: 46-55.
3. Chung, S.B., 1998. A new pruning algorithm for structural Optimization of Neural Networks. Masters Thesis, Department of Electrical Engineering, KAIST, Taejon, Korea.
4. Costa, M.A., A. Braga and B.R. de Menezes, 2002. Constructive and Pruning Methods for Neural Network Design. Proc. of the VII Brazilian Symposium on Neural Networks (SBRN = 02).
5. Le Cun, Y., J.S. Denker and S.A. Solla, 1990. AOptimal Brain Damage., Proc. of the advances in Neural Information processing (2), Touretzky, D.S. (Ed.), pp: 598-605.
6. Eleuteri, A., R. Tagliaferri andL. Milano, 2005. A novel information geometric approach to variable selection in MLP networks. Neural Networks, 18: 1309-1318.
7. Engelbrecht, A.P., 2001. A New Pruning Heuristic Based on Variance Analysis of Sensitivity Information. IEEE Trans. Neural Networks, 12: 1386-399.
8. Fahlman, S.E. and C. Lebiere, 1990. The cascade-correlation learning architecture. Proc. of the Advances in Neural Information Processing System 2. Touretzky, D.S. (Ed.), pp: 524-532.
9. Fogel, D.B., 1995. Evolutionary Computation: Towards a New Philosophy of Machine Intelligence. New York, pp: 10017-2394: IEEE. Press.
10. Hagiwara, M., 1994. Simple and effective method for removal of hidden units and weights. Neurocomputing, 6: 207-218.
11. Hassibi, B. andD.G. Stork,1993. Second-order derivatives for network pruning: Optimal Brain Surgeon., proc. of the advances in Neural Information Processing Systems.
12. Lee Giles, C, S.J. Hanson and J.D. Cowan, Haykin, S., 2003. A Neural Networks: A Comprehensive Foundation (2nd Edn.), Pearson Education 5: 164-171.
13. Huang, G.B., P. Saratchandran andN. Sundararajan, 2005. Generalized Growing and Pruning RBF (CGAP-RBF) Neural Network for Function Approximation. IEEE Trans. Neural Networks, 16: 57-67.
14. Islam, M.M., X. Yao and K. Murase, 2003. Constructive Algorithm for Training Cooperative Neural Network Ensemble. IEEETrans. Neural Networks, 14: 820-832.
15. Kwok, T.Y. and D.Y. Yeung, 1999. Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Trans. Neural Networks, 8: 630-645.
16. Lee, H. and C.H. Park, 2002. A Pruning Algorithm of Neural Networks using Impact Factor Regularization. Proc. of the 9th International Conference on Neural Information Processing (ICONIP)., 5: 2605-2609.
17. Miller, G.F., P.M. Todd and S.U. Hedge, 1989. Designing neural networks using genetic algorithms. Proc. of the 3rd International Conference on Genetic Algorithms and their Applications. Schaffer, J.D. (Ed.), Morgan Kaufmann, San Mateo, CA, pp: 379-384.
18. Mozer, M.C. and P. Smolensky, 1989. Skeletonization: A technique for trimming the fat from a network via relevance assessment. Proc. Adv. Neural Network Information Processing (1), Touretzky, D.S. (Ed.), pp: 107-115.
19. Odri, S.V., D.P. Petrovacki and G.A. Krstonosic, 1993. Evolutional development of a multilevel neural network. Neural Networks, 6: 583-595.
20. Prechelt, L., 1995. Some notes on neural learning algorithm benchmarking. Neurocomputing, 9: 343-347.
21. Prechelt, L., 1996. A quantitative study of experimental evaluation of neural network learning algorithms. Neural Network, 9: 457-462.
22. Prechelt, L., 1994. Probenl- A set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms. University Karlsruhe, Karlsruhe
23. Germany. Reed, R., 1993. Pruning Algorithm-A survey. IEEE Trans. Neural Networks, 4: 740-747.
24. Shahjahan, M. and K. Murase, 2003. Dynamic Neuron Decaying Method for Pruning Artificial Neural Networks., E86-D: 736-751.
25. Xiang, C, Q. Ding and T. H. Lee, 2005. Geometric Interpretation and Architecture Selection of MLP. IEEE Trans. Neural Networks, 16: 84-96.
26. Yao, X. and Y. Liu, 1997. A new evolutionary system for evolving artificial neural networks. IEEE Trans. Neural Networks, 8: 694-713.
27. Yeung, D.S. and Xiao-Qin Zeng, 92002. Hidden neuron pruning for multilayer perceptrons using a sensitivity measure A. Proc. of the 1 st International Conference on Machine Learning and Cybernetics, Beijing, pp: 1751-1757.