Abstract
Recent theory work has shown that a Genetic Program (GP) used to produce programs may have output that is bounded above by the GP itself [l]. This paper presents proofs that show that 1) a program that is the output of a GP or any inductive process has complexity that can be bounded by the Kolmogorov complexity of the originating program; 2) this result does not hold if the random number generator used in the evolution is a true random source; a nd 3) an optimization problem being solved with a GP will have a complexity that can be bounded below by the growth rate of the minimum length problem representation used for the implementation. These results are then used to provide guidance for GP implementation.
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
Rylander, B.: On GP Complexity, Proceedings of the Genetic and Evolutionary Computation Conference Workshop Program (2000), pp. 309–311
Soule, T., Foster, J., Dickinson, J.: Using Genetic Programming to Approximate Maximum Cliques, Proceedings Genetic Programming Conference (1998), pp. 400–405
Li, M., Vitanyi, P.: Kolmogorov Complexity and its Applications, Handbook of Theoretical Computer Science Volume A. Algorithms and Complexity, pp. 189–254. The MIT Press, Cambridge, Massachusetts (1990)
O’Reilly, U.: An Analysis of Genetic Programming, Doctoral Thesis, School of Computer Science, Carleton University, Ottawa, Ontario, Canada (1995), pp. 14
Rylander, B., Foster, J.: GA-Hard Problems, Proceedings of the Genetic and Evolutionary Computation Conference (2000), pp. 367
Rylander, B., Foster, J.: Computational Complexity and Genetic Algorithms, Proceedings of the World Science and Engineering Society’s Conference on Soft Computing (2001)
Rylander, B., Foster, J.: Genetic Algorithms, and Hardness, Proceedings of the World Science and Engineering Society’s Conference on Soft Computing (2001)
Langdon, W., Soule, T., Poli, R., Foster, J.: The Evolution of Size and Shape, Advances in Genetic Programming Volume III, pp. 163–190. The MIT Press, Cambridge, Massachusetts (1999)
Soule, T., Foster, J., Dickinson, J.: Code Growth in Genetic Programming, Proceedings Genetic Programming Conference (1996), pp. 215–223
Rylander, B., Soule, T., Foster, J.: Quantum Genetic Algorithms, proceedings of the Genetic and Evolutionary Computation Conference (2000), pp. 373
Ge, Y., Watson, L., Collins, E.: Genetic Algorithms for Optimization on a Quantum Computer, Unconventional Models of Computation, Springer-Verlag, London (1998)
Narayan, A., Moore, M.: Quantum Inspired Genetic Algorithms, Technical Report 344, Department of Computer Science, University of Exeter, England (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rylander, B., Soule, T., Foster, J. (2001). Computational Complexity, Genetic Programming, and Implications. In: Miller, J., Tomassini, M., Lanzi, P.L., Ryan, C., Tettamanzi, A.G.B., Langdon, W.B. (eds) Genetic Programming. EuroGP 2001. Lecture Notes in Computer Science, vol 2038. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45355-5_28
Download citation
DOI: https://doi.org/10.1007/3-540-45355-5_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41899-3
Online ISBN: 978-3-540-45355-0
eBook Packages: Springer Book Archive