Exploring and comparing the best "direct methods" for the efficient training of MLP-networks

IEEE Transactions on Neural Networks

Volumn 7, Issue 6, 1996, Pages 1497-1502

  Di Martino, M ^a   Fanelli, S ^a   Protasi, M ^a  

^a UNIVERSITY OF ROME TOR VERGATA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0039610507     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.548177     Document Type: Review

References (13)

1. F. Bärmann and F. Biegler-König, "On a class of efficient learning algorithms for neural networks," Neural Networks, vol. 5, pp. 139-144, 1992.
2. _, "A learning algorithm for multilayered neural networks based on linear least squares problems," Neural Networks, vol. 6, pp. 127-131, 1993.
3. F. Bärmann, T. Gervens, M. Renner, and W. Schlagner, "Prognose des Korrosionsverhältens von Werkstoffen in hochkonzentrierter Schwefelsäure mit Hilfe neuronaler Netze," Werkstoffe und Korrosion, vol. 44, pp. 467-472, 1993.
4. F. Bärmann, G. R. Greye, and A. Lieberam, "Einsatz Neuronaler Netze zur Prognose von thermophysikalischen Stoffkonstanten reiner Stoffe aus Strukturinformationen," Chem. Ing. Tech., vol. 65, no. 3, pp. 310-314, 1993.
5. R. Battiti, "First- and second-order methods for learning: Between steepest descent and Newton's methods," Neural Computa., vol. 4, pp. 141-166, 1992.
6. M. Di Martino, S. Fanelli, and M. Protasi, "An efficient algorithm for the binary classification of patterns using MLP networks," in Proc. 2nd IEEE Int. Conf. Neural Networks, San Francisco, CA, 1993, pp. 936-943.
7. _, "A new improved on-line algorithm for multidecisional problems based on MLP-networks using a limited amount of information," in Proc. 1st Int. Joint Conf. Neural Networks, Nagoya, Japan, 1993, pp. 617-620.
8. _, "Computational experiences of new direct methods for the online training of MLP networks with binary outputs," in Proc. It Int. Conf. Artificial Neural Networks, Sorrento, Italy, 1994, pp. 627-630.
9. S. Fanelli, P. Paparo, and M. Protasi, "Improving performances of Battiti-Shanno's quasi-Newtonian algorithms for learning in MLP networks," in Proc. 2nd Australian and New Zealand Conf. Intell. Inform. Syst., Brisbane, Australia, 1994, pp. 115-119.
10. R. Fletcher and C. H. Reeves, "Function minimization by conjugate gradients," Comput. J., vol. 7, 1964.
11. P. Franzoi, O. G. Johnson, and G. G. Pieroni, "Comparing the performance of the generalized delta rule with singular value decomposition-based global algorithms for simple vision tasks," in Proc. 4th Italian Wkshp.: Parallel Architectures and Neural Nets, Vietri sul Mare, Italy, 1991, pp. 181-190.
12. B. Noble, "Methods for computing the Moore-Penrose generalized inverse, and related matters," in Generalized Inverses and Applications, M. Zuhair Nashed, Ed. New York: Academic, 1976.
13. J. Ortega and W. Rheinboldt, Iterative Solution of Nonlinear Equations in Several Variables. New York: Academic, 1970.