Abstract
This paper proposes a new framework, referred to as Recurrent Bayesian Genetic Programming (rbGP), to sustain steady convergence in Genetic Programming (GP) (i.e., to prevent premature convergence) and effectively improves its ability to find superior solutions that generalise well. The term ‘Recurrent’ is borrowed from the taxonomy of Neural Networks (NN), in which a Recurrent NN (RNN) is a special type of network that uses a feedback loop, usually to account for temporal information embedded in the sequence of data points presented to the network. Unlike RNN, our algorithm’s temporal dimension pertains to the sequential nature of the evolutionary process itself, and not to the data sampled from the problem solution space. rbGP introduces an intermediate generation between each subsequent generation in order to collect information about the offspring’s fitness distribution of each parent. Placing the collected information into a Bayesian model, rbGP predicts the probability of any individual to produce offspring fitter than its parent. This predicted probability (calculated by the Bayesian model) is used by the tournament selection instead of the original fitness value. Empirical evidence, from 13 problems, against canonical GP, demonstrates that rbGP preserves generalisation in most cases.
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.
Similar content being viewed by others
References
Altenberg, L.: The evolution of evolvability in genetic programming. In: Kinnear Jr., K.E. (ed.) Advances in Genetic Programming, ch. 3, pp. 47–74. MIT Press (1994)
Bassett, J.K., Coletti, M., De Jong, K.A.: The relationship between evolvability and bloat. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, GECCO 2009, pp. 1899–1900. ACM, New York (2009)
Ducheyne, E., De Baets, B., De Wulf, R.: Is fitness inheritance useful for real-world applications? In: Fonseca, C.M., Fleming, P.J., Zitzler, E., Deb, K., Thiele, L. (eds.) EMO 2003. LNCS, vol. 2632, pp. 31–42. Springer, Heidelberg (2003)
Ellison, A.M.: Bayesian inference in ecology. Ecology Letters 7(6), 509–520 (2004)
Fakeih, A., Kattan, A.: Recurrent genetic algorithms: Sustaining evolvability. In: Hao, J.-K., Middendorf, M. (eds.) EvoCOP 2012. LNCS, vol. 7245, pp. 230–242. Springer, Heidelberg (2012)
Google. Google insights (June 2013), http://www.google.com/trends/
Hasegawa, Y., Iba, H.: A Bayesian network approach to program generation. IEEE Transactions on Evolutionary Computation 12(6), 750–764 (2008)
Hu, T.: Evolvability and Rate of Evolution in Evolutionary Computation. PhD thesis, Department of Computer Science, Memorial University of Newfoundland, ST. John’s, Newfoundland, Canada (May 2010)
Hu, T., Banzhaf, W.: Evolvability and speed of evolutionary algorithms in light of recent developments in biology. J. Artif. Evol. App. 2010, 1:1–1:28 (2010)
Murphy, G.P.: Manipulating Convergenc. In: Evolutionary Systems. PhD thesis, University of Limerick, Ireland (May 19, 2009)
Peacock, J.A.: Two-dimensional goodness-of-fit testing in astronomy. Royal Astronomical Society, Monthly Notices 202, 615–627 (1983)
Poli, R., Langdon, W.W.B., McPhee, N.F.: Field Guide to Genetic Programming. Lulu Enterprises Uk Limited (2008)
Smith, R.E., Dike, B.A., Stegmann, S.A.: Fitness inheritance in genetic algorithms. In: Proceedings of the 1995 ACM Symposium on Applied Computing, SAC 1995, pp. 345–350. ACM, New York (1995)
Wang, Y., Wineberg, M.: The estimation of evolvability genetic algorithm. In: The 2005 IEEE Congress on Evolutionary Computation, vol. 3, pp. 2302–2309 (September 2005)
Yanai, K., Iba, H.: Estimation of distribution programming based on bayesian network. In: The 2003 Congress on Evolutionary Computation, CEC 2003, vol. 3, pp. 1618–1625 (2003)
Zhang, B.-T.: Bayesian genetic programming. In: Haynes, T., Langdon, W.B., O’Reilly, U.-M., Poli, R., Rosca, J. (eds.) Foundations of Genetic Programming, Orlando, Florida, USA, pp. 68–70 (July 13, 1999)
Zhang, B.-T.: Bayesian methods for efficient genetic programming. Genetic Programming and Evolvable Machines 1(3), 217–242 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kattan, A., Ong, YS. (2015). Bayesian Inference to Sustain Evolvability in Genetic Programming. In: Handa, H., Ishibuchi, H., Ong, YS., Tan, K. (eds) Proceedings of the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems, Volume 1. Proceedings in Adaptation, Learning and Optimization, vol 1. Springer, Cham. https://doi.org/10.1007/978-3-319-13359-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-13359-1_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13358-4
Online ISBN: 978-3-319-13359-1
eBook Packages: EngineeringEngineering (R0)