Abstract
This paper deals with the topic of learning through neuroevolutionary algorithms in non-stationary settings. This kind of algorithms that evolve the parameters and/or the topology of a population of Artificial Neural Networks have provided successful results in optimization problems in stationary settings. Their application to non-stationary problems, that is, problems that involve changes in the objective function, still requires more research. In this paper we address the problem through the integration of implicit, internal or genotypic, memory structures and external explicit memories in an algorithm called Promoter Based Genetic Algorithm with External Memory (PBGA-EM). The capabilities introduced in a simple genetic algorithm by these two elements are shown on different tests where the objective function of a problem is changed in an unpredictable manner.
This work was supported by the MEC of Spain through project CIT-370300-2007-18, DPI2006-15346-C03-01 and DEP2006-56158-C03-02.
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
Yao, X.: Evolving artificial neural networks. Proc. of the IEEE 87(9), 1423–1447 (1999)
Trojanowski, K., Michalewicz, Z.: Evolutionary Approach to Non-stationary Optimisation Tasks. LNCS, vol. 1609, pp. 538–546 (1999)
Mori, N., Kita, H., Nishikawa, Y.: Adaptation to a Changing Environment by Means of the Feedback Thermodynamical Genetic Algorithm. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H.-P. (eds.) PPSN 1998. LNCS, vol. 1498, pp. 149–158. Springer, Heidelberg (1998)
Dasgupta, D., MacGregor, D.R.: Nonstationary function optimization using the structured genetic algorithm. Proceedings Parallel Problem Solving from Nature 2, 145–154 (1992)
Ryan, C., Collins, J.J., Wallin, D.: Non-stationary Function Optimization Using Polygenic Inheritance. LNCS, vol. 2724, pp. 1320–1331 (2003)
Eggermont, J., Lenaerts, T.: Non-stationary Function Optimization using Evolutionary Algorithms with a Case-based Memory, Technical Report TR 2001-11 (2001)
D’Silva, T., Janik, R., Chrien, M., Stanley, K., Miikkulainen, R.: Retaining Learned Behavior During Real-Time Neuroevolution. In: Procedings AIIDE (2005)
Cobb, H.G.: An investigation into the use of hypermutation as an adaptive operator in genetic algorithms having continuous, time-dependent nonstationary environments, NRL Memorandum Report 6760, 523-529 (1990)
Moriarty, D.E.: Symbiotic Evolution of Neural Networks in Sequential Decision Tasks, PhD thesis, University of Texas at Austin, Tech. Rep. UT-AI97-257 (1997)
Gomez, F., Burger, D., Miikkulainen, R.: A neuroevolution method for dynamic resource allocation on a chip multiprocessor. In: Proc. Int. Joint Conf. on Neural Networks (2001)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10, 99–127 (2002)
Dasgupta, D., McGregor, D.: Designing application-specific neural networks using the structured genetic algorithm. In: Proceedings COGANN 1992, pp. 87–96 (1992)
Branke, J.: Memory enhanced evolutionary algorithms for changing optimization problems. In: Proceedings CEC 1999, vol. 3, pp. 1875–1882 (1999)
Bellas, F., Duro, R.J.: Introducing Long Term Memory in an ANN Based Multilevel Darwinist Brain. LNCS, vol. 2686, pp. 590–597 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bellas, F., Becerra, J.A., Duro, R.J. (2008). Internal and External Memory in Neuroevolution for Learning in Non-stationary Problems. In: Asada, M., Hallam, J.C.T., Meyer, JA., Tani, J. (eds) From Animals to Animats 10. SAB 2008. Lecture Notes in Computer Science(), vol 5040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69134-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-69134-1_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69133-4
Online ISBN: 978-3-540-69134-1
eBook Packages: Computer ScienceComputer Science (R0)