Evaluation of robustness and performance of Early Stopping Rules with Multi Layer Perceptrons

Proceedings of the International Joint Conference on Neural Networks

Volumn , Issue , 2009, Pages 1877-1884

  Lodwich, Aleksander ^a   Rangoni, Yves ^a   Breuel, Thomas ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC TRAINING; CLASSIFICATION TASKS; EARLY STOPPING; ENSEMBLE LEARNING; ERROR BACK-PROPAGATION; MULTI-LAYER PERCEPTRONS; OVERFITTING; STOCHASTIC GRADIENT DESCENT; STOPPING RULE; TRAINING TIME;

CYBERNETICS; NEURAL NETWORKS; PATTERN RECOGNITION SYSTEMS;

WIRELESS SENSOR NETWORKS;

EID: 70449378059     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2009.5178626     Document Type: Conference Paper

References (17)

1. Rich Caruana and Ru Niculescu-Mizil, An Empirical Comparison of Supervised Learning Algorithms, In Proc. 23rd Intl. Conf. Machine learning (ICML'06), pp. 161-168, 2006
2. D. Saad, On-Line Learning in Neural Networks, Cambridge University Press, 1998
3. R. Ganguli and S. Bandopadhyay, Neural network performance versus network architecture for a quick stop training application. Application of Computers and Operations Research in the Mineral Industries, South African Institute of Mining and Met al.lurgy, 2003
4. Rich Caruana and Alexandru Niculescu-Mizil and Geoff Crew and Alex Ksikes, Ensemble selection from libraries of models, in Proceedings of the twenty-first international conference on Machine learning, ICML'04, p. 18, ACM, New York, 2004
5. Jurgen Branke, Evolutionary algorithms for neural network design and training, In Proceedings of the First Nordic Workshop on Genetic Algorithms and its Applications, pp. 145-163, 1995
6. William Finno, Ferdinand Hergert and Hans Georg Zimmermann, Improving model selection by nonconvergent methods. Neural Networks Vol. 6, pp 771-783, 1993.
7. Lutz Prechelt, Early stopping - but when, Neural Networks: Tricks of the Trade, volume 1524 of LNCS, chapter 2, pp. 55-69, Springer-Verlag, 1998
8. Lutz Prechelt, Automatic early stopping using cross validation: quantifying the criteria, Neural Networks, pp. 761-767, 1998
9. Mahesh S. Iyer and R. Russell Rhinehart, A novel method to stop neural network training, American Control Conference, 2000. Proceedings of the 2000, Vol. 2, pp. 929-933, Chicago, USA, 2000
10. Thomas Breuel, Pattern Recognition Engineering (PaREn) http://sites.google.com/a/iupr.com/paren-project/Home
11. Yann Le Cun, Leon Bottou and Genevieve Orr and Klauss-Robert MullerEfficient BackProp, http://www.research.att.com/leonb/PS/lecun-98b. ps.gz, 1998
12. Lutz Prechelt, PROBEN1 - A Set of Neural Network Benchmarking Problems and Benchmarking Rules, Technical Report 21/94, Faculty of Computer Science, University of Karlsruhe, 1994
13. Yann LeCun, The MNIST database, http://yann. lecun. com/exdb/mnist/index.html
14. S. E. Fahlman:An empirical study of learning speed in backpropagation networks CMU-CS-88-162, 1988
15. Koch W., Schulz E. M., Wright R., Smith R. M., Lang S., et al.What is a Ratio Scale?, Rasch Measurement Transactions 9:4, p. 457, 1996
16. Rajendra Bhatia, The Logarithmic Mean, Resonance, pp. 583-594, June, Bangalore, 2008
17. http://archive.ics.uci.edu/ml /UCI Machine Learning Repository