Abstract
In this work we present an application of the Confidence Interval Based Crossover using L 2 Norm (CIXL2) and BLX-α crossovers to the evolution of neural networks. CIXL2 is a new crossover operator, based on obtaining the statistical features of the best individuals of the population. These features are used as virtual parents for the crossover operator.
Due to the permutation problem of neural network coding that negatively affects the crossover operator, we have adopted a novel approach. Crossover is made at node level. Instead of performing crossover over two whole networks, we perform crossover over two nodes. We present here the adaptation of two crossover methods: CIXL2 and BLX-α. All the nodes of the best networks are clustered, by means of a k-means algorithm, and a redefinition of the operators is carried out using the obtained clusters. Each node is mated within the cluster where it belongs.
This work was supported in part by the Project TIC2002-04036-C05-02 of the Spanish CICYT and FEDER funds.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
P. J. Angeline, G. M. Saunders, and Jordan B. Pollack. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5(1):54–65, January 1994.
L. J. Eshelman and J. D. Schaffer. Real-coded genetic algorithms and intervalschemata. In L. D. Whitley, editor, Foundations of Genetic Algorithms 2, pages 187–202. Morgan Kaufmann, San Mateo, 1993.
D. E. Goldberg. Genetic algorithms and Walsh functions: Part 1, a gentle introduction. Complex Systems, 3:129–152, 1989.
C. Hervás-Martínez, D. Ortiz-Boyer, and N. García-Pedrajas. Theoretical analysis of the confidence interval based crossover for real-coded genetic algorithms. In J. Merelo, P. Adamidis, H-G. Beyer, J. Fernández, and H-P. Schwefel, editors, Parallel Problem Solving from Nature— PPSN VII, number 2439 in Lecture Notes in Computer Science, pages 153–161, Granada, september 2002. Springer-Verlag.
G. F. Miller, P. M. Todd, and S. U. Hedge. Designing neural networks. Neural Networks, 4:53–60, 1991.
D. E. Moriarty and R. Miikkulainen. Forming neural networks through efficient and adaptive coevolution. Evolutionary Computation, 4(5), 1998.
D. Ortiz-Boyer, C. Hervás-Martínez, and N. García-Pedrajas. Crossover operator effect in function optimization with constraints. In J. Merelo, P. Adamidis, H-G. Beyer, J. Fernández, and H-P. Schwefel, editors, Parallel Problem Solving from Nature— PPSN VII, number 2439 in Lecture Notes in Computer Science, pages 184–193, Granada, september 2002. Springer-Verlag.
D. Thierens. Non-redundant genetic coding of neural networks. In Proc. of the 1996 IEEE International Conference on Evolutionary Computation, pages 571–575, Piscataway, NJ, 1996. IEEE Press.
X. Yao. Evolving artificial neural networks. Proceedings of the IEEE, 9(87):1423–1447, 1999.
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
Sanz-Tapia, E., García-Pedrajas, N., Ortiz-Boyer, D., Hervás-Martínez, C. (2003). Node level crossover applied to neural network evolution. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_66
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_66
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive