Abstract
This article proposes a context-free grammar to be used in grammar-guided genetic programming systems to automatically design feed-forward neural architectures. This grammar has three important features. The sentences that belong to the grammar are binary strings that directly encode all the valid neural architectures only. This rules out the appearance of illegal points in the search space. Second, the grammar has the property of being ambiguous and semantically redundant. Therefore, there are alternative ways of reaching the optimum. Third, the grammar starts by generating small networks. This way it can efficiently adapt to the complexity of the problem to be solved. From the results, it is clear that these three properties are beneficial to the convergence process of the grammar-guided genetic programming system.
This is a preview of subscription content, log in via an institution to check access.
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
Raidl, G.: Evolutionary computation: An overview and recent trends. OGAI Journal 2, 2–7 (2005)
Whigham, P.: Grammatically-based genetic programming. In: Proc. of the Workshop on Genetic Programming: From Theory to Real-World Apps., pp. 33–41 (1995)
Haykin, S.: Neural Networks: A Comprehensive Foundation., 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
Koza, J., Rice, J.: Genetic generation of both the weight and architecture for a neural network. In: Proceedings of the International Joint Conference on Neural Networks, vol. II, pp. 397–404 (1991)
Manrique, D., Rios, J., Rodriguez-Paton, A.: Evolutionary system for automatically constructing and adapting radial basis function networks. Neurocomputing 69, 2268–2283 (2006)
Hussain, T.S.: Attribute grammar encoding based upon a generic neural markup language: Facilitating the design of theoretical neural network models. In: Proc. of the International Joint Conference on Neural Networks, vol. I, pp. 25–29 (2004)
Yong, C., Stanley, K., Miikkulainen, R., Karpov, I.: Incorporating advice into neuroevolution of adaptive agents. In: Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (2006)
Stanley, K., Bryant, B., Miikkulainen, R.: Real-time neuroevolution in the NERO video game. IEEE Transactions on Evolutionary Computation 9, 653–668 (2005)
Barrios, D., Carrascal, A., Manrique, D., Ríos, J.: Cooperative binary-real coded genetic algorithms for generating and adapting artificial neural networks. Neural Computing and Applications 12, 49–60 (2003)
Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Networks 2, 183–192 (1989)
Manrique, D., Márquez, F., Ríos, J., Rodríguez-Patón, A.: Grammar based crossover operator in genetic programming. In: Mira, J., Álvarez, J.R. (eds.) IWINAC 2005. LNCS, vol. 3562, pp. 252–261. Springer, Heidelberg (2005)
Hoai, N., Shan, Y., McKay, R.: Is ambiguity useful or problematic for grammar guided genetic programming? A case study. In: 4th Asia-Pacific Conference on Simulated Evolution and Learning, pp. 449–454 (2002)
Woodward, J., Neil, J.: No free lunch, program induction and combinatorial problems. In: Proceedings of Genetic Programming, pp. 475–484 (2003)
Woodward, J.: GA or GP? that is not the question. In: Proceedings of the Congress on Evolutionary Computation, pp. 1056–1063 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Couchet, J., Manrique, D., Porras, L. (2007). Grammar-Guided Neural Architecture Evolution. In: Mira, J., Álvarez, J.R. (eds) Bio-inspired Modeling of Cognitive Tasks. IWINAC 2007. Lecture Notes in Computer Science, vol 4527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73053-8_44
Download citation
DOI: https://doi.org/10.1007/978-3-540-73053-8_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73052-1
Online ISBN: 978-3-540-73053-8
eBook Packages: Computer ScienceComputer Science (R0)