An empirical evaluation of constructive neural network algorithms in classification tasks

International Journal of Innovative Computing and Applications

Volumn 1, Issue 1, 2007, Pages 2-13

  Nicoletti, Maria do Carmo ^a   Bertini, João R ^a  

^a FEDERAL UNIVERSITY OF SÃO CARLOS   (Brazil)

Author keywords

CoNN; constructive neural network algorithms; neural networks; NNs

Indexed keywords

EID: 84951714199     PISSN: 1751648X     EISSN: 17516498     Source Type: Journal    
DOI: 10.1504/IJICA.2007.013397     Document Type: Article

References (33)

1. Amaldi, E. and Guenin, B. (1997) ‘Two constructive methods for designing compact feedfoward networks of threshold units’, International Journal of Neural System, Vol. 8, Nos. 5–6, pp.629–645.
2. Bertini Jr., J.R., Nicoletti, M.C. and Hruschka Jr., E.R. (2006) ‘A comparative evaluation of constructive neural networks methods using PRM and BCP as TLU training algorithms’, Proceedings of the IEEE SMC 2006, Taiwan.
3. Blake, C.L. and Merz, C.J. (1998) UCI Repository of Machine Learning Databases, Irvine, CA: University of California, Department of Information and Computer Science.
4. Burgess, N. (1994) ‘A constructive algorithm that converges for real-valued input patterns’, International Journal of Neural Systems, Vol. 5, No. 1, pp.59–66.
5. Campbell, C. (1997) ‘Constructive learning techniques for designing neural network systems’, in C.T. Leandes (Ed). Neural Network Systems Technologies and Applications, San Diego: Academic Press.
6. Fahlman, S. and Lebiere, C. (1990) ‘The cascade correlation architecture’, Advances in Neural Information Processing Systems, Vol. 2, San Mateo, CA: Morgan Kaufman, pp.524–532.
7. Frean, M. (1990) ‘The upstart algorithm: a method for constructing and training feedforward neural networks’, Neural Computation, Vol. 2, pp.198–209.
8. Frean, M. (1992) ‘A thermal perceptron learning rule’, Neural Computation, Vol. 4, pp.946–957.
9. Gallant, S.I. (1986a) ‘Optimal linear discriminants’, Proceedings of the Eighth International Conference on Pattern Recognition, pp.849–852.
10. Gallant, S.I. (1986b) ‘Three constructive algorithms for network learning’, Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Amherst, MA, pp.652–660.
11. Gallant, S.I. (1990) ‘Perceptron-based learning algorithms’, Proceedings of the IEEE Transactions on Neural Networks, Vol. 1, No. 2, pp.179–191.
12. Gallant, S.I. (1994) Neural Network Learning and Expert Systems, London, England: The MIT Press.
13. Giles, C.L., Chen, D., Sun, G-Z., Chen, H-H., Lee, Y-C. and Goudreau, M.W. (1995) ‘Constructive learning of recurrent neural network: limitations of recurrent cascade correlation and a simple solution’, IEEE Transactions on Neural Networks, Vol. 6, No. 4, pp.829–836.
14. Gosling, J., Joy, B., Steele, G. and Bracha, G. (2000) Java Language Specification, 2nd edition, Addison Wesley Professional.
15. Jia, J. and Chua, H-C. (1995) ‘Solving two-spiral problem through input data representation’, Proceedings of the IEEE International Conference on Neural Networks, Vol. 1, pp.132–135.
16. Krauth, W. and Mézard, M. (1987) ‘Learning algorithms with optimal stability in neural networks’, Journal of Physics A, Vol. 20, pp.745–752.
17. Kremer, S.C. (1996) ‘Comments on ‘Constructive learning of recurrent neural networks: limitations of recurrent cascade correlation and a simple solution’, IEEE Transactions on Neural Networks, Vol. 7, No. 4, p.1047.
18. Kwok, T-Y. and Yeung, D-Y. (1999) ‘Constructive algorithms for structure learning in feedforward neural networks for regression problems’, IEEE Transactions on Neural Networks, Vol. 8, pp.630–645.
19. Mayoraz, E. and Aviolat, F. (1996) ‘Constructive training methods for feedforward neural networks with binary weights’, International Journal of Neural Networks, Vol. 7, pp.149–166.
20. Mézard, M. and Nadal, J. (1989) ‘Learning feedforward networks: the tiling algorithm’, Journal of Physics A: Mathematical and General, Vol. 22, pp.2191–2203.
21. Moller, M.F. (1993) ‘A scaled conjugate gradient algorithm for fast supervised learning’, Neural Networks, Vol. 6, pp.525–533.
22. Parekh, R., Yang, J. and Honavar, V. (1995) ‘Constructive neural network learning algorithms for multi-category classification’, Technical Report ISU-CS-TR95–15a, Department of CS, Iowa State University, USA.
23. Parekh, R., Yang, J. and Honavar, V. (1997a) ‘MUpstart – a constructive neural network learning algorithm for multi-category pattern classification’, Proceedings of the IEEE/INNS International Conference on Neural Networks (ICNN’97), Vol. III, pp.1924–1929.
24. Parekh, R., Yang, J. and Honavar, V. (1997b) ‘Pruning strategies for the MTiling constructive learning algorithm’, Proceedings of the IEEE/INNS International Conference on Neural Networks (ICNN’97), Vol. III, pp.1960–1965.
25. Parekh, R., Yang, J. and Honavar, V. (1997c) ‘Constructive neural network learning algorithms for multi-class real-valued pattern classification’, Technical Report ISU-CS-TR97–06, Department of CS, Iowa State University, USA.
26. Parekh, R., Yang, J. and Honavar, V. (2000) ‘Constructive neural-network learning algorithms for pattern classification’, IEEE Transactions on Neural Networks, Vol. 11, No. 2, pp.436–451.
27. Poulard, H. (1995) ‘Baricentric correction procedure: a fast method for learning threshold unit’, Proceedings of WCNN 95, Vol. 1, pp.710–713.
28. Poulard, H. and Estève, D. (1995) ‘A convergence theorem for barycentric correction procedure’, Technical Report 95180, LAAS-CNRS, Toulouse, France.
29. Reed, R. (1993) ‘Pruning algorithms – a survey’, IEEE Transactions on Neural Networks, Vol. 4, No. 5, pp.740–747.
30. Rosenblatt, F. (1962) Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Washington, DC: Spartan Press.
31. Saffery, J. and Thornton, C. (1991) ‘Using stereographic projection as a pre-processing technique for Upstart’, Proceedings of the International Joint Conference on Neural Networks of the IEEE, pp.441–446.
32. Smieja, F.J. (1993) ‘Neural network constructive algorithms: trading generalization for learning efficiency?’ Circuits, Systems and Signal Processing, Vol. 12, pp.331–374.
33. Volpini, P., Figueira, L.B., Colafemina, J.F. and Roque, A.C. (2002) ‘A neural network-based system for diagnosis of central vestibular lesion’, Proceedings of METMBS’02, pp.29–33.