Some numerical aspects of the training problem for feed-forward neural nets

Neural Networks

Volumn 10, Issue 8, 1997, Pages 1455-1463

  McKeown, John J ^a   Stella, Fabio ^b   Hall, Gary ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

^b UNIVERSITY OF MILAN   (Italy)

Author keywords

Feed forward neural net training; Non uniqueness; Nonlinear least squares; Numerical ill conditioning

Indexed keywords

LEARNING ALGORITHMS; LEARNING SYSTEMS; LEAST SQUARES APPROXIMATIONS;

NEURAL NETWORK TRAINING;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CONDITIONING; NONLINEAR SYSTEM; PRIORITY JOURNAL; TRAINING;

EID: 0031277459     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(97)00015-4     Document Type: Article

References (13)

1. Dixon, L. C. W. and Szego, G. P. (1975). Towards global optimisation. Amsterdam/New York: North-Holland//American Elsevier.
2. Dixon, L. C. W. and Szego, G. P. (1978). Towards global optimisation 2. Amsterdam/New York: North-Holland//American Elsevier.
3. Dixon, L. C. W. and Mills, D. J. (1991). Neural networks and nonlinear optimization I: the representation of continuous functions. Numerical Optimisation Centre Technical Report 252. University of Hertfordshire, College Lane, Hatfield.
4. Ellacott, S. W. (1993). The numerical analysis approach. In J. Taylor (Ed.), Mathematical approaches to neural networks. (pp. 103-137). Amsterdam: Elsevier Science Publishers B.V.
5. Gorse, D., Shepherd, A. and Taylor, J. G. (1994). A classical algorithm for avoiding local minima. 1994 International Neural Network Society Annual Meeting, San Diego, California (Volume 3).
6. McKeown, J. J. (1975). Specialised versus general-purpose algorithms for minimizing functions that are sums of squared terms. Mathematical Programming, 9, 57-68.
7. McKeown, J. J. (1980). Sensitivity analysis with respect to independent variables. In L. C. W. Dixon, E. Spedicato and G. P. Szego (Eds.), Nonlinear optimisation, theory and algorithms. Boston: Birkhauser.
8. McKeown, J. J., Meegan, D., & Sprevak, D. (1990). An introduction to unconstrained optimisation: a computer illustrated text. Bristol and New York: Adam Hilger.
9. Rinnooy kan, A. H. G. and Timmer, G. T. (1987). Towards global optimization methods (I and II). Math Prog., 39, 27-78.
10. Saarinen, S., Bramley, R. and Cybenko, G. (1991) Ill-conditioning in neural network training problems. CSRD Report 1089, Center for Supercomputing Research and Development, University of Illinois, Urbana, ILL.
11. Törn, A. and Zilinskas, A. (1987). Global optimization. Lecture notes in computer science. Berlin, Heidelberg: Springer-Verlag.
12. Ratschek, H. and Rokne, J. (1988). New computer methods for global optimization. Chichester: Ellis Horwood Ltd.
13. van der Smagt, P. (1994). Minimisation methods for training feedforward neural networks. Neural Networks, 7(1), 1-11.