Natural Computing

, Volume 2, Issue 2, pp 117–132 | Cite as

Neutrality and self-adaptation

  • Christian Igel
  • Marc Toussaint


Neutral genotype-phenotype mappings can be observed in natural evolution and are often used in evolutionary computation. In this article, important aspects of such encodings are analyzed.

First, it is shown that in the absence of external control neutrality allows a variation of the search distribution independent of phenotypic changes. In particular, neutrality is necessary for self-adaptation, which is used in a variety of algorithms from all main paradigms of evolutionary computation to increase efficiency.

Second, the average number of fitness evaluations needed to find a desirable (e.g., optimally adapted) genotype depending on the number of desirable genotypes and the cardinality of the genotype space is derived. It turns out that this number increases only marginally when neutrality is added to an encoding presuming that the fraction of desirable genotypes stays constant and that the number of these genotypes is not too small.

evolutionary computation genotype-phenotype mapping neutrality No-Free-Lunch theorem redundancy self-adaptation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Angeline PJ (1996) Two self-adaptive crossover operations for genetic programming. In: Angeline P and Kinnear K (eds) Advances in Genetic Programming, Vol. 2. MIT Press, CambridgeGoogle Scholar
  2. Bäck T (1992) Self-adaptation in genetic algorithms. In: Varela FJ and Bourgine P (eds) Towards a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, pp. 263–271. MIT Press, Cambridge, MAGoogle Scholar
  3. Bäck T (1998) An overview of parameter control methods by self-adaptation in evolutionary algorithms. Fundamenta Informaticae 35(1–4): 51–66Google Scholar
  4. Banzhaf W, Nordin P, Keller RE and Francone FD (1998) Genetic Programming – An Introduction; On the Automatic Evolution of Computer Programs and its Applications. Morgan Kaufmann, dpunkt.verlagGoogle Scholar
  5. Barnett L (1998) Ruggedness and neutrality – The NKp family of fitness landscapes. In: Adami C, Belew RK, Kitano H and Taylor CE (eds) Alive VI: Sixth International Conference on Articial Life, pp. 18–27. MIT Press, Cambridge, MAGoogle Scholar
  6. Conrad M (1990) The geometry of evolution. Biosystems 24: 61–81Google Scholar
  7. Ebner M, Langguth P, Albert J, Shackleton M and Shipman R (2001) On neutral networks and evolvability. In: Proceedings of the 2001 Congress on Evolutionary Computation (CEC 2001), pp. 1–8. IEEE PressGoogle Scholar
  8. Eiben AE, Hinterding R and Michalewicz Z (1999) Parameter control in evolutionary algorithms. IEEE Transactions on Evolutionary Computation 3(2): 124–141Google Scholar
  9. Fogel DB (1995) Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE PressGoogle Scholar
  10. Fogel LJ, Angeline PJ and Fogel DB (1995) An evolutionary programming approach to selfadaptation on finite state machines. In: McDonnell JR, Reynolds RG and Fogel DB (eds) Proceedings of the Fourth Annual Conference on Evolutionary Programming, pp. 355–365. MIT PressGoogle Scholar
  11. Graham RL, Knuth DE and Patashnik O (1994) Concrete Mathematics: A Foundation for Computer Science. Addison-Wesley, 2 editionGoogle Scholar
  12. Huynen MA (1996) Exploring phenotype space through neutral evolution. Journal of Molecular Evolution 43: 165–169Google Scholar
  13. Igel C and Kreutz M (2003) Operator adaptation in evolutionary computation and its application to structure optimization of neural networks. Neurocomputing, in pressGoogle Scholar
  14. Igel C and Stagge P (2002) Effects of phenotypic redundancy in structure optimization. IEEE Transactions on Evolutionary Computation 6(1): 74–85Google Scholar
  15. Igel C and Toussaint M (2003) On classes of functions for which no free lunch results hold. Information Processing Letters, in pressGoogle Scholar
  16. Kimura M (1968) Evolutionary rate at the molecular level. Nature 217: 624–626Google Scholar
  17. Mahner M and Kary M (1997) What exactly are genomes, genotypes and phenotypes? And what about phenomes? Journal of Theoretical Biology 186(1): 55–63Google Scholar
  18. Newman MEJ and Engelhardt R (1998) Effects of neutral selection on the evolution of molecular species. Proceedings of the Royal Society of London, Series B: Biological Sciences 265(1403): 1333–1338Google Scholar
  19. Radcliffe NJ (1991) Equivalence class analysis of genetic algorithms. Complex Systems 5: 183–205Google Scholar
  20. Rechenberg I (1994) Evolutionsstrategie '94, Werkstatt Bionik und Evolutionstechnik. Frommann-Holzboog, StuttgartGoogle Scholar
  21. Schaffer JD and Morishima A (1987) An adaptive crossover distribution mechanism for genetic algorithms. In: Grefenstette JJ (ed) Proceedings of the Second International Conference on Genetic Algorithms (ICGA'87), pp. 36–40. Lawrence Erlbaum Associates, Cambridge, MAGoogle Scholar
  22. Schumacher C, Vose MD and Whitley LD (2001) The no free lunch and description length. In: Spector L, Goodman E, Wu A, Langdon W, Voigt H-M, Gen M, Sen S, Dorigo M, Pezeshk S, Garzon M and Burke E (eds) Genetic and Evolutionary Computation Conference (GECCO 2001), pp. 565–570. Morgan KaufmannGoogle Scholar
  23. Schuster P (1996) Landscapes and molecular evolution. Physica D 107: 331–363Google Scholar
  24. Schuster P (2002) Molecular insights into evolution of phenotypes. In: Crutchfield JP and Schuster P (eds) Evolutionary Dynamics – Exploring the Interplay of Accident, Selection, Neutrality and Function, Santa Fe Institute Series in the Science of Complexity. Oxford University PressGoogle Scholar
  25. Schwefel H-P (1977) Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie, Vol. 26 of Interdisciplinary Systems Research. Birkhäuser Verlag, BaselGoogle Scholar
  26. Schwefel H-P (1995) Evolution and Optimum Seeking, Sixth-Generation Computer Technology Series. John Wiley & Sons, New YorkGoogle Scholar
  27. Shackleton MA, Shipman R and Ebner M (2000) An investigation of redundant genotypephenotype mappings and their role in evolutionary search. In: Zalzala A, Fonseca C, Kim J-H and Smith A (eds) Proceedings of the International Congress on Evolutionary Computation (CEC 2000), pp. 493–500. IEEE Press, Piscataway, NJGoogle Scholar
  28. Shipman R (1999) Genetic redundancy: Desirable or problematic for evolutionary adaptation. In: Bedau MA, Rasmussen S, McCaskill JS and Packard NH (eds) Proceedings of the 4th International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA), pp. 337–344. Springer-VerlagGoogle Scholar
  29. Smith JE and Fogarty TC (1997) Operator and parameter adaptation in genetic algorithms. Soft Computing 1(2), 81–87Google Scholar
  30. Stephens CR and Waelbroeck H (1999) Codon bias and mutability in HIV sequences. Journal of Molecular Evolution 48: 390–397Google Scholar
  31. Toussaint M (2001) Self-adaptive exploration in evolutionary search. Technical Report IRINI 2001-05, Institut für Neuroinformatik, Lehrstuhl für Theoretische Biologie, Ruhr-Universität Bochum, 44780 Bochum, GermanyGoogle Scholar
  32. Toussaint M (2003) On the evolution of phenotypic exploration distributions. In: Cotta C, De Jong K, Poli R and Rowe J (eds) Foundations of Genetic Algorithms 7 (FOGA VII). Morgan Kaufmann, in pressGoogle Scholar
  33. Toussaint M and Igel C (2002) Neutrality: A necessity for self-adaptation. In: IEEE Congress on Evolutionary Computation 2002 (CEC 2002), pp. 1354–1359. IEEE PressGoogle Scholar
  34. van Nimwegen E, Crutchfield JP and Huynen M (1999) Neutral evolution of mutational robustness. Proceedings of the National Academy of Sciences 96: 9716–9720Google Scholar
  35. Weicker K and Weicker N (2000) Burden and benefits of redundancy. In: Martin WN and Spears WM (eds) Foundations of Genetic Algorithms 6 (FOGA 6), pp. 313–333. Morgan KaufmannGoogle Scholar
  36. Wilke CO (2001) Adaptive evolution on neutral networks. Bulletin of Mathematical Biology 63, 715–730Google Scholar
  37. Wolpert DH and Macready WG (1997) No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation 1(1), 67–82Google Scholar
  38. Zhigljavsky AA (1991) Theory of global random search. Kluwer Academic PublishersGoogle Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Christian Igel
    • 1
  • Marc Toussaint
    • 1
  1. 1.Lehrstuhl für theoretische Biologie, Institut für NeuroinformatikRuhr-Universität BochumBochumGermany

Personalised recommendations