Stopped training via algebraic online estimation of the expected test-set error

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 2, Issue , 1997, Pages 1088-1092

  Utans, J ^a  

^a LONDON BUSINESS SCHOOL   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

GENERALIZATION PERFORMANCE; ITERATIVE OPTIMIZATION; LOCAL MINIMUMS; NEURAL NETWORK MODEL; OBJECTIVE FUNCTIONS; ON-LINE ESTIMATION; OVERFITTING; STOPPING TIME;

NEURAL NETWORKS; ALGEBRA; APPROXIMATION THEORY; ERROR ANALYSIS; FUNCTIONS; ITERATIVE METHODS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; OPTIMIZATION;

ITERATIVE METHODS; NEURAL NETWORKS;

ALGEBRAIC ONLINE ESTIMATION;

EID: 0030718027     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.616180     Document Type: Conference Paper

References (11)

1. A. Barron. Predicted squared error: a criterion for automatic model selection. In S. Farlow, editor, Self-Organizing Methods in Modeling. Marcel Dekker, New York, 1984.
2. Y. Chauvin. Generalization dynamics in LMS trained linear networks. In R. P. Lippman, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 3, pages 890-896. Morgan Kaufmann Publishers, San Mateo, CA, 1991.
3. W. Finnoff, F. Hergert, and H. G. Zimmermann. Improving model selection by nonconvergent methods. Neural Net-works, 6:771-783,1993.
4. S. Geman, E. Bienenstock, and R. Doursat. Neural networks and the bias/variance dilemma. Neural Computation, 4( 1): 1-58,1992.
5. J. Larsen. A generalization error estimate for nonlinear systems. In Proceedings of the 1992 IEEE Workshop on Neural Networks for Signal Processing, pages 29-38. IEEE Service Center, Piscataway, NJ, 1992.
6. T. K. Leen and G. B. Orr. Weight-space probability densities and convergence times for stochastic learning. In Int. Joint Conference on Neural Networks, volume 4, pages 158-164, Baltimore, MD, 1992.
7. J. Moody and J. Utans. Architecture selection strategies for neural networks: Application to corporate bond rating prediction. In A. N. Refenes, editor, Neural Networks in the Captial Markets. John Wiley & Sons, 1994.
8. J. E. Moody. Note on generalization, regularization and architecture selection in nonlinear learning systems. In B. H. Juang, S. Y. Kung, and C. A. Kamm, editors, Neural Networks for Signal Processing, pages 1-10. IEEE Signal Processing Society, 1991.
9. J. Sjoberg and L. Ljung. Overtraining, regularization, and searching for minimum in neural networks, technical Report LiTH-ISY-I-1297, Dept. of Electrical Engineering, Linkoping University, S-581 83 Linkoping, Sweden, February 1992.
10. M. Stone. Cross-validation: A review. Math. Operations-forsch. Statist., Ser. Statistics, 9(1), 1978.
11. A. S. Weigend and D. E. Rummelhart. The effective dimension of the space of hidden units. In Proceedings of the International Joint Conference on Neural Networks, volume III, pages 2069-2074, Singapore, 1991.