Abstract
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments considered a feedforward neural network trained with standard backpropagation and 15 public-domain and artificial data sets. In most cases, the pruned networks seemed to have better or equal accuracy than the original fully-connected networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found large differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87 (1999) 1423–1447
Castillo, P.A., Arenas, M.G., Castillo-Valdivieso, J.J., Merelo, J.J., Prieto, A., Romero, G.: Artificial neural networks design using evolutionary algorithms. In: Proceedings of the Seventh World Conference on Soft Computing. (2002)
Pelikan, M., Goldberg, D.E., Cantú-Paz, E.: BOA: The Bayesian optimization algorithm. In Banzhaf, W., Daida, J., Eiben, A.E., Garzon, M.H., Honavar, V., Jakiela, M., Smith, R.E., eds.: Proceedings of the Genetic and Evolutionary Computation Conference 1999: Volume 1, San Francisco, CA, Morgan Kaufmann Publishers (1999) 525–532
Etxeberria, R., Larrañaga, P.: Global optimization with Bayesian networks. In: II Symposium on Artificial Intelligence (CIMAF99). (1999) 332–339
Mühlenbein, H., Mahnig, T.: FDA-A scalable evolutionary algorithm for the optimization of additively decomposed functions. Evolutionary Computation 7 (1999) 353–376
Reed, R.: Pruning algorithms—a survey. IEEE Transactions on Neural Networks 4 (1993) 740–747
Whitley, D., Starkweather, T., Bogart, C.: Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel Computing 14 (1990) 347–361
Hancock, P.J.B.: Pruning neural networks by genetic algorithm. In Aleksander, I., Taylor, J., eds.: Proceedings of the 1992 International Conference on Artificial Neural Networks. Volume 2., Amsterdam, Netherlands, Elsevier Science (1992) 991–994
LeBaron, B.: An evolutionary bootstrap approach to neural network pruning and generalization. unpublished working paper (1997)
Schmidt, M., Stidsen, T.: Using GA to train NN using weight sharing, weight pruning and unit pruning. Technical report, Aarhus University, Computer Science Department, Aarhus, Denmark (1995)
Whitley, D., Bogart, C.: The evolution of connectivity: Pruning neural networks using genetic algorithms. Technical Report CS-89-113, Colorado State University, Department of Computer Science, Fort Collins (1989)
Thierens, D.: Scalability problems of simple genetic algorithms. Evolutionary Computation 7 (1999) 331–352
Pelikan, M., Goldberg, D.E., Lobo, F.: A survey of optimization by building and using probabilistic models. IlliGAL Report No. 99018, University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, Urbana, IL (1999)
Larrañaga, P., Etxeberria, R., Lozano, J.A., Peña, J.M.: Optimization by learning and simulation of Bayesian and Gaussian networks. Tech Report No. EHU-KZAAIK-4/99, University of the Basque Country, Conostia-San Sebastian, Spain (1999)
Harik, G.R., Lobo, F.G., Goldberg, D.E.: The compact genetic algorithm. In: Proceedings of the 1998 IEEE International Conference on Evolutionary Computation, Piscataway, NJ, IEEE Service Center (1998) 523–528
Baluja, S.: Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning. Tech. Rep. No. CMU-CS-94-163, Carnegie Mellon University, Pittsburgh, PA (1994)
Mühlenbein, H.: The equation for the response to selection and its use for prediction. Evolutionary Computation 5 (1998) 303–346
Harik, G.: Linkage learning via probabilistic modeling in the ECGA. IlliGAL Report No. 99010, University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, Urbana, IL (1999)
Lobo, F.G., Harik, G.R.: Extended compact genetic algorithm in C++. IlliGAL Report No. 99016, University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, Urbana, IL (1999)
Pelikan, M.: A simple implementation of the Bayesian optimization algorithm (BOA) in C++ (version 1.0). IlliGAL Report No. 99011, University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, Urbana, IL (1999)
Blake, C., Merz, C.: UCI repository of machine learning databases (1998)
Inza, I., Larrañaga, P., Etxeberria, R., Sierra, B.: Feature subset selection by Bayesian networks based on optimization. Artificial Intelligence 123 (1999) 157–184
Lim, T.J., Loh, W.Y., Shih, Y.S.: A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms. Machine Learning 40 (2000) 203–228
Alpaydin, E.: Combined 5 × 2cv F test for comparing supervised classification algorithms. Neural Computation 11 (1999) 1885–1892
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cantú-Paz, E. (2003). Pruning Neural Networks with Distribution Estimation Algorithms. In: Cantú-Paz, E., et al. Genetic and Evolutionary Computation — GECCO 2003. GECCO 2003. Lecture Notes in Computer Science, vol 2723. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45105-6_93
Download citation
DOI: https://doi.org/10.1007/3-540-45105-6_93
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40602-0
Online ISBN: 978-3-540-45105-1
eBook Packages: Springer Book Archive