Avoiding overfitting with BP-SOM

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2, Issue , 1997, Pages 1140-1145

  Weijters, Ton ^a   Van Den Herik, H Jaap ^a   Van Den Bosch, Antal ^a   Postma, Eric ^a  

^a MAASTRICHT UNIVERSITY   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION LEARNING; FEED-FORWARD NETWORK; GENERALISATION; HYBRID NEURAL NETWORKS; KOHONEN; MULTI-LAYERED; OVERFITTING; WEIGHT DECAY;

NEURAL NETWORKS;

BACKPROPAGATION;

EID: 49249094378     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Y. Le Cun, J. Denker, and S. Solla. Optimal brain damage. In D. S. Touretzky, editor, Advances in Neural Information Processing Systems, volume 2, pages 598-605. Morgan Kaufmann, San Mateo, CA, 1990.
2. S. E. Fahlman and C. Lebiere. The cascade-correlation learning architecture. Technical Report CMU-CS-90-100, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, 1990.
3. B. Hassibi, D. G. Stork, and G. J. Wolff. Optimal brain surgeon and general network pruning. Technical Report CRC-TR-9235, RICOH California Research Centre, 1992.
4. G. E. Hinton. Learning distributed representation of concepts. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, pages 1-12, Hillsdale, NJ, 1986. Erlbaum.
5. M. I. Jordan and C. M. Bishop. Neural networks. Technical Report A.I. Memo No. 1562, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 1996.
6. T. Kohonen. Self-organisation and Associative Memory, volume 8 of Series in Information Sciences. Springer-Verlag, Berlin, 1984.
7. M. C. Mozer and P. Smolensky. Using relevance to reduce network size automatically. Connection Science, 1:3-16, 1989.
8. D. Norris. How to build a connectionist idiot (savant). Cognition, 35:277-291, 1989.
9. L. Prechelt. Probenl: A set of neural network benchmark problems and benchmarking rules. Technical Report 19/94, Fakultat fur Informatik, Universitat Karlsruhe, Germany, 1994.
10. J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, CA, 1993.
11. J. Rissanen. A universal prior for integers and estimation by minimum description length. Annals of Statistics, 11:416-431, 1983.
12. D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing: Explorations in the Micro structure of Cognition, volume 1: Foundations, pages 318-362. The MIT Press, Cambridge, MA, 1986.
13. C. Shaffer. Overfltting avoidance as bias. Machine Learning, 10:153-178, 1993.
14. C. Thornton. Measuring the difficulty of specific learning problems. Connection Science, 7:81-92, 1995.
15. A. S. Weigend, D. E. Rumelhart, and B. A. Huberman. Generalization by weight-elimination with application to forecasting. In R. P. Lippman, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems, volume 3, pages 875-882. Morgan Kaufmann, San Mateo, CA, 1990.
16. A. S. Weigend. On overfltting and the effective number of hidden units. In M. C. Mozer, P. Smolensky, D. S. Touretzky, J. L. Elman, and A. S. Weigend, editors, Proceedings of the 1998 Connectionist Models Summer School, pages 335-342, 1994.
17. A. Weijters. The BP-SOM architecture and learning rule. Neural Processing Letters, 2:13-16, 1995.
18. D. H. Wolpert. On overfltting avoidance as bias. Technical Report SFI TR 92-03-5001, The Santa Fe Institute, 1992.