Living organisms function according to complex mechanisms that operate in different ways depending on conditions. Evolutionary theory suggests that such mechanisms evolved as result of a random search guided by selection. However, there has existed no theory that would explain quantitatively which mechanisms can so evolve in realistic population sizes within realistic time periods, and which are too complex. In this paper we suggest such a theory. Evolution is treated as a form of computational learning from examples in which the course of learning is influenced only by the fitness of the hypotheses on the examples, and not otherwise by the specific examples. We formulate a notion of evolvability that quantifies the evolvability of different classes of functions. It is shown that in any one phase of evolution where selection is for one beneficial behavior, monotone Boolean conjunctions and disjunctions are demonstrably evolvable over the uniform distribution, while Boolean parity functions are demonstrably not. The framework also allows a wider range of issues in evolution to be quantified. We suggest that the overall mechanism that underlies biological evolution is evolvable target pursuit, which consists of a series of evolutionary stages, each one pursuing an evolvable target in our technical sense, each target being rendered evolvable by the serendipitous combination of the environment and the outcome of previous evolutionary stages.


Ideal Function Turing Machine Parity Function Neutral Mutation Statistical Query 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bäck, T., Fogel, D.B., Michalewicz, Z. (eds.): Handbook of Evolutionary Computation. Oxford Univ. Press, Oxford (1997)zbMATHGoogle Scholar
  2. 2.
    Bejerano, G., et al.: Ultraconserved elements in the human genome. Science 304, 1321–1325 (2004)CrossRefGoogle Scholar
  3. 3.
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Learnability and the Vapnik Chervonenkis dimension. J. ACM 36(4), 929–965 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Bürger, R.: The Mathematical Theory of Selection, Recombination, and Mutation. Wiley, Chichester (2000)zbMATHGoogle Scholar
  5. 5.
    Darwin, C.: On the origin of species by means of natural selection. John Murray, London (1859)Google Scholar
  6. 6.
    Dermitzakis, E.T., et al.: Conserved non-genic sequences - an unexpected feature of mammalian genomes. Nature Reviews Genetics 6, 151–157 (2005)CrossRefGoogle Scholar
  7. 7.
    Drake, J.W., et al.: Rates of spontaneous mutation. Genetics 148, 1667–1686 (1998)Google Scholar
  8. 8.
    Ehrenfeucht, A., Haussler, D., Kearns, M., Valiant, L.G.: A general lower bound on the number of examples needed for learning. Inf. and Computation 82(2), 247–261 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Fischer, P., Simon, H.U.: On learning ring-sum expressions. SIAM J. Computing 21(1), 181–192 (1992)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Fisher, R.A.: The Genetical Theory of Natural Selection. Oxford University Press, Oxford (1930)zbMATHGoogle Scholar
  11. 11.
    Garey, M.R., Johnson, D.S.: Computers and Intractability: a Guide to the Theory of NP-Completeness. Freeman, San Francisco (1979)zbMATHGoogle Scholar
  12. 12.
    Helmbold, D., Sloan, R., Warmuth, M.K.: Learning integer lattices. SIAM J. Computing 21(2), 240–266 (1992)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Amer. Stat. Assoc. 58, 13 (1963)zbMATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Kearns, M.: Efficient noise tolerant learning from statistical queries. J. ACM 45(6), 983–1006 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Kearns, M., Valiant, L.G.: Cryptographic limitations on learning Boolean formulae. J. ACM 41(1), 67–95 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Kearns, M., Vazirani, U.: An Introduction to Computational Learning Theory. MIT Press, Cambridge (1994)Google Scholar
  17. 17.
    Kimura, M.: Evolutionary rate at the molecular level. Nature 217, 624–626 (1968)CrossRefGoogle Scholar
  18. 18.
    Kumar, S., Subramanian, S.: Mutation rates in mammalian genomes. Proc. Nat. Acad. Sci. 99, 803–808 (2002)CrossRefGoogle Scholar
  19. 19.
    Papadimitriou, C.H.: Computational Complexity. Addison-Wesley, Reading, Mass (1994)zbMATHGoogle Scholar
  20. 20.
    Pitt, L., Valiant, L.G.: Computational limitations on learning from examples. J. ACM 35(4), 965–984 (1988)zbMATHCrossRefMathSciNetGoogle Scholar
  21. 21.
    Roff, D.A.: Evolutionary Quantitative Genetics. Chapman & Hall, New York (1997)Google Scholar
  22. 22.
    Ros, J.P.: Learning Boolean functions with genetic algorithms: A PAC analysis. In: Whitley, L.D. (ed.) Foundations of Genetic Algorithms, pp. 257–275. Morgan Kaufmann, San Mateo, CA (1993)Google Scholar
  23. 23.
    Valiant, L.G.: A theory of the learnable. C. ACM 27(11), 1134–1142 (1984)zbMATHCrossRefGoogle Scholar
  24. 24.
    Valiant, L.G.: Robust logics. Artificial Intelligence Journal 117, 231–253 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Valiant, L.G.: Knowledge infusion. In: Proc. 21st National Conference on Artificial Intelligence, AAAI 2006, pp. 1546–1551 (2006)Google Scholar
  26. 26.
    Wagner, G.P., Altenberg, L.: Complex adaptations and the evolution of evolvability. Evolution 50(3), 967–976 (1996)CrossRefGoogle Scholar
  27. 27.
    Wegener, I.: Theoretical aspects of evolutionary algorithms. In: Orejas, F., Spirakis, P.G., van Leeuwen, J. (eds.) ICALP 2001. LNCS, vol. 2076, pp. 64–78. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  28. 28.
    Wright, S.: Evolution and the Genetics of Populations, A Treatise. University of Chicago Press, Chicago (1968-78)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Leslie G. Valiant
    • 1
  1. 1.School of Engineering and Applied Sciences, Harvard University 

Personalised recommendations