From multilayer perceptrons to radial basis function networks: A comparative study

2004 IEEE Conference on Cybernetics and Intelligent Systems

Volumn , Issue , 2004, Pages 69-74

  Ding, S Q ^a   Xiang, C ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

MLP; Neural Networks; RBFN

Indexed keywords

EXPONENTIAL CIRCULAR BACKPROPAGATION (ECBP); NEURONS; RADIAL BASIS FUNCTION NETWORK (RBFN);

ALGEBRA; APPROXIMATION THEORY; BACKPROPAGATION; COMPUTER NETWORKS; FUNCTIONS; MATHEMATICAL MODELS;

MULTILAYER NEURAL NETWORKS;

EID: 11244259262     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Bishop, C., "Neural Networks for Pattern Recognition," Oxford University Press, 1995.
2. Haykin, S., "Neural networks: a comprehensive foundation," Prentice Hall, New Jersey, second edition, 1999.
3. Ridella, S., Rovetta, S. and Zunino, R., "Circular backpropagation networks for classification", IEEE Transactions on Neural Networks, vol. 8, no. 1, pp. 84-97, 1997.
4. Maruyama, M., Girosi F., and Poggio T., "A connection between GRBF and MLP", A.I. Memo, No. 1291, MIT Artificial Intelligence Lab, 1992.
5. Wilensky, G. and N. Manukian, "The projection neural networks," International Joint Conference on Neural Networks (IJCNN92), II, pp. 358-367, 1992.
6. Wilamowski, B. M. and Jaeger, R. C. "Implementation of RBF type networks by MLP networks," Proceedings of the IEEE International Conference on Neural Networks (ICNN96), pp. 1670-1675. 1996.
7. Omohundro, S. M. "Geometric learning algorithms," Technical Report 89-041, International Computer Science Institute, Berkeley, CA. 1989.
8. Casasent, D. and E. Barnard, "Adaptive clustering neural net for picewise nonlinear discriminant surfaces," International Joint Conference on Neural Networks, I, pp. 423-427, 1992.
9. Mor, J.J., "The Levenberg-Marquardt Algorithm: implementation and theory, in numerical analysis," G. A. Watson, ed., Lecture Notes in Mathematics, vol. 630, Springer-Verlag, Berlin, pp. 105-116, 1977
10. Nguyen, D. and B. Widrow, "Improving the learning speed of 2-layer neural network by choosing initial values of the adaptive weights," in Proceedings of International Joint Conference on Neural Networks (IJCNN-90), vol. 3, pp. 21-26, 1990.
11. Caruana, R., Lawrence, S., and Giles, C. L., "Overfilling in Neural Networks: Backpropagation, Conjugate Gradient, and Early Stopping," Neural Information Processing Systems, Denver, Colorado, Vol. 13, pp.402-408, 2001.
12. Xiang, C., S.Q. Ding, and T.H. Lee, "Geometrical Interpretation and Architecture Selection of MLP", to appear in IEEE Transactions on Neural Networks, 2005.
13. Sarle, W., 2002 "How many hidden layers should I use?," Newsgroup:comp.ai.neural-nets FAQ, Available at: ftp://frp.sas.com/pub/neural/ FAQ3.html#A_hl.
14. Fahlmmann, S. E., and C. Lebiere, "The cascade-correlation learning architecture", in Advances in Neural Information Processing Systems II, San Mateo, CA: Morgan Kaufmann, pp. 524-532, 1989.
15. Chen, S., B. Mulgrew, and P. M. Grant, "A clustering technique for digital communications channel equalization using radial basis function networks", IEEE Transactions on Neural Networks, Vol. 4, no. 4, pp. 570-579, 1993.
16. Su, M.C., and C.H.Chou, "A modified version of the k-means algorithm with a distance based on cluster symmetry," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, No. 6, pp. 674-680, 2001.