Robust Formulations for Training Multilayer Perceptrons

Neural Computation

Volumn 16, Issue 4, 2004, Pages 837-862

  Kärkkäinen, Tommi ^a   Heikkola, Erkki ^a  

^a UNIVERSITY OF JYVÄSKYLÄ   (Finland)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 12144285657     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976604322860721     Document Type: Article

References (32)

1. Bartlett, P. L. (1998). The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network. IEEE Trans. Inform. Theory, 44(2), 525-536.
2. Bishop, C. M. (1995). Neural networks for pattern recognition, Oxford: Oxford University Press.
3. Broomhead, D. S., & Lowe, D. (1988). Multivariable functional interpolation and adaptive networks. Complex Systems, 2(3), 321-355.
4. Chen, D. S., & Jain, R. C. (1994). A robust backpropagation learning algorithm for function approximation. IEEE Transactions on Neural Networks, 5(3), 467-479.
5. Clarke, F. H. (1983). Optimization and nonsmooth analysis. New York: Wiley.
6. Flake, G. W. (1998). Square unit augmented, radially extended, multilayer perceptrons. In G. B. Orr & K.-R. Müller (Eds.), Neural networks: Tricks of the trade (pp. 145-163). Berlin: Springer-Verlag.
7. Hagan, M., & Menhaj, M. (1994). Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), 989-993.
8. Haykin, S. (1994). Neural networks: A comprehensive foundation. New York: Macmillan.
9. Hettmansperger, T. P., & McKean, J. W. (1998). Robust nonparametric statistical methods. London: Edward Arnold.
10. Huber, P. J. (1981). Robust statistics. New York: Wiley.
11. Kärkkäinen, T. (2002). MLP-nerwork in a layer-wise form with applications to weight decay. Neural Computation, 14(6), 1451-1480.
12. Kärkkäinen, T., & Heikkola, E. (2002). Robust MLP (Rep. No. C 1), Jyväskylä: University of Jyväskylä, Department of Mathematical Information Technology
13. Kärkkäinen, T., & Majava, K. (2000). Determination of regularization parameter in monotone active set method for image restoration. In P. Neittaanmäki, T. Tiihonen, & P. Tarvainen (Eds.), Proceedings of the Third European Conference on Numerical Mathematics and Advanced Applications (pp. 641-648). Singapore: World Scientific.
14. Kärkkäinen, T., Majava, K., & Mäkelä, M. M. (2001). Comparison of formulations and solution methods for image restoration problems. Inverse Problems, 17(6), 1977-1995.
15. 1 -norm and related methods (pp. 217-230). Amsterdam: North-Holland.
16. Kosko, B. (1992). Neural networks and fuzzy systems: A dynamical systems approach to machine intelligence. Englewood Cliffs, NJ: Prentice Hall.
17. Liano, K. (1996). Robust error measure for supervised neural network learning with outliers. IEEE Transactions on Neural Networks, 7(1), 246-250.
18. Mäkelä, M. M., & Neittaanmäki, P. (1992). Nonsmooth optimization. River Edge, NJ: World Scientific.
19. Milasevic, P., & Ducharme, G. (1987). Uniqueness of the spatial median. Ann. Statist., 75(3), 1332-1333.
20. Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill.
21. Nocedal, J., & Wright, S. J. (1999). Numerical optimization. New York: Springer-Verlag.
22. Oja, H. (1999). Affine invariant multivariate sign and rank tests and corresponding estimates: A review. Scand. J. Statist., 26(3), 319-343.
23. Prechelt, L. (1998). Early stopping-but when? In G. B. Orr & K.-R. Müller (Eds.), Neural networks: Tricks of the trade (pp. 55-70). Berlin: Springer-Verlag.
24. 1-norm, in statistical inference. Sankhyā Ser. A, 50(3), 289-313.
25. Raudys, Š. (1998a). Evolution and generalization of a single neurone: I. Single-layer perceptron as seven statistical classifiers. Neural Networks, 11(2), 283-296.
26. Raudys, Š. (1998b). Evolution and generalization of a single neurone: II. Complexity of statistical classifiers and sample size considerations. Neural Networks, 11 (2), 297-313.
27. Raudys, Š. (2000). Evolution and generalization of a single neurone: III. Primitive, regularized, standard, robust and minimax regressions. Neural Networks, 33(4-5), 507-523.
28. Rögnvaldsson, T. S. (1998). A simple trick for estimating the weight decay parameter. In G. B. Orr & K.-R. Müller (Eds.), Neural networks: Tricks of the trade (pp. 71-92). Berlin: Springer-Verlag.
29. Rousseeuw, P. J., & Leroy, A. M. (1987). Robust regression and outlier detection. New York: Wiley.
30. Saito, K., & Nakano, R. (2000). Second-order learning algorithm with squared penalty term. Neural Computation, 12(3), 709-729.
31. Sarajedini, A., & Hecht-Nielsen, R. (1992). The best of both worlds: Casasent networks integrate multilayer perceptrons and radial basis functions. In International Joint Conference on Neural Networks, 1992 (Vol. 3, pp. 905-910). Piscataway, NJ: IEEE.
32. Sarle, W. (1997). The comp.ai.neural-nets frequently asked questions list. Available on-line at: http://www.faqs.org/faqs/ai-faq/neural-nets/(part2/section-14.html).