Advertisement

Observation of Unbounded Novelty in Evolutionary Algorithms is Unknowable

  • Eric Holloway
  • Robert Marks
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10841)

Abstract

Open ended evolution seeks computational structures whereby creation of unbounded diversity and novelty are possible. However, research has run into a problem known as the “novelty plateau” where further creation of novelty is not observed. Using standard algorithmic information theory and Chaitin’s Incompleteness Theorem, we prove no algorithm can detect unlimited novelty. Therefore observation of unbounded novelty in computer evolutionary programs is nonalgorithmic and, in this sense, unknowable.

References

  1. 1.
    Mitchell, M., Forrest, S.: Genetic algorithms and artificial life. Artif. life 1(3), 267–289 (1994)CrossRefGoogle Scholar
  2. 2.
    Huneman, P.: Determinism, predictability and open-ended evolution: lessons from computational emergence. Synthese 185(2), 195–214 (2012)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Komosinski, M., Rotaru-Varga, A.: From directed to open-ended evolution in a complex simulation model. Artif. Life 7, 293–299 (2000)Google Scholar
  4. 4.
    Sayama, H.: Seeking open-ended evolution in swarm chemistry. In: 2011 IEEE Symposium on Artificial Life (ALIFE), pp. 186–193. IEEE (2011)Google Scholar
  5. 5.
    Li, J., Storie, J., Clune, J.: Encouraging creative thinking in robots improves their ability to solve challenging problems. In: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation, pp. 193–200. ACM (2014)Google Scholar
  6. 6.
    Soros, L., Stanley, K.O.: Identifying necessary conditions for open-ended evolution through the artificial life world of chromaria. Artif. life 14, 793–800 (2014)Google Scholar
  7. 7.
    Basener, W.F.: Exploring the concept of open-ended evolution. In: Biological Information: New Perspectives, pp. 87–104. World Scientific (2012)Google Scholar
  8. 8.
    Bedau, M.A., McCaskill, J.S., Packard, N.H., Rasmussen, S., Adami, C., Green, D.G., Ikegami, T., Kaneko, K., Ray, T.S.: Open problems in artificial life. Artif. life 6(4), 363–376 (2000)CrossRefGoogle Scholar
  9. 9.
    Ruiz-Mirazo, K., Peretó, J., Moreno, A.: A universal definition of life: autonomy and open-ended evolution. Orig. Life Evol. Biosph. 34(3), 323–346 (2004)CrossRefGoogle Scholar
  10. 10.
    Ruiz-Mirazo, K., Umerez, J., Moreno, A.: Enabling conditions for open-ended evolution. Biol. Philos. 23(1), 67–85 (2008)CrossRefGoogle Scholar
  11. 11.
    Bonabeau, E., Dorigo, M., Theraulaz, G.: Swarm Intelligence: from Natural to Artificial Systems, vol. 1. Oxford University Press, Oxford (1999)MATHGoogle Scholar
  12. 12.
    Ewert, W., Marks, R.J., Thompson, B.B., Yu, A.: Evolutionary inversion of swarm emergence using disjunctive combs control. IEEE Trans. Syst. Man Cybern. Syst. 43(5), 1063–1076 (2013)CrossRefGoogle Scholar
  13. 13.
    Roach, J., Ewert, W., Marks, R.J., Thompson, B.B.: Unexpected emergent behaviors from elementary swarms. In: 2013 45th Southeastern Symposium on System theory (SSST), pp. 41–50. IEEE (2013)Google Scholar
  14. 14.
    Roach, J.H., Marks, R.J., Thompson, B.B.: Recovery from sensor failure in an evolving multiobjective swarm. IEEE Trans. Syst. Man Cybern. Syst. 45(1), 170–174 (2015)CrossRefGoogle Scholar
  15. 15.
    Taylor, T.: Exploring the concept of open-ended evolution. In: Proceedings of the 13th International Conference on Artificial life, pp. 540–541 (2012)Google Scholar
  16. 16.
    Jakobi, N.: Encoding scheme issues for open-ended artificial evolution. In: Voigt, H.-M., Ebeling, W., Rechenberg, I., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 52–61. Springer, Heidelberg (1996).  https://doi.org/10.1007/3-540-61723-X_969CrossRefGoogle Scholar
  17. 17.
    Channon, A.: Three evolvability requirements for open-ended evolution. In: Artificial Life VII Workshop Proceedings, Portland, OR, pp. 39–40 (2000)Google Scholar
  18. 18.
    Mueller, I.: Euclid’s elements and the axiomatic method. Br. J. Philos. Sci. 20(4), 289–309 (1969)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Shenoy, P.P., Shafer, G.: Axioms for probability and belief-function propagation. In: Yager, R.R., Liu, L. (eds.) Classic Works of the Dempster-Shafer Theory of Belief Functions. STUDFUZZ, vol. 219, pp. 499–528. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-44792-4_20CrossRefGoogle Scholar
  20. 20.
    Chaitin, G.J.: Algorithmic information theory. IBM J. Res. Dev. 21(4), 350–359 (1977)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Raatikainen, P.: On interpreting Chaitin’s incompleteness theorem. J. Philos. Log. 27(6), 569–586 (1998)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Chaitin, G.J.: Information, Randomness & Incompleteness: Papers on Algorithmic Information Theory, vol. 8. World Scientific, Singapore (1990)CrossRefGoogle Scholar
  23. 23.
    Grünwald, P.D., Vitányi, P.M., et al.: Algorithmic information theory. In: Handbook of the Philosophy of Information, pp. 281–320 (2008)CrossRefGoogle Scholar
  24. 24.
    Seibt, P.: Algorithmic Information Theory. Springer, Heidelberg (2006).  https://doi.org/10.1007/978-3-540-33219-0CrossRefMATHGoogle Scholar
  25. 25.
    Van Lambalgen, M.: Algorithmic information theory. J. Symb. Log. 54(4), 1389–1400 (1989)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Chaitin, G.: Proving Darwin: Making Biology Mathematical. Vintage, New York (2012)MATHGoogle Scholar
  27. 27.
    Chaitin, G.J.: Toward a mathematical definition of life. In: Information, Randomness & Incompleteness: Papers on Algorithmic Information Theory, pp. 86–104. World Scientific (1987)CrossRefGoogle Scholar
  28. 28.
    Gecow, A.: The purposeful information. On the difference between natural and artificial life. Dialogue Univers. 18(11/12), 191–206 (2008)CrossRefGoogle Scholar
  29. 29.
    Pattee, H.H.: Artificial life needs a real epistemology. In: Morán, F., Moreno, A., Merelo, J.J., Chacón, P. (eds.) ECAL 1995. LNCS, vol. 929, pp. 21–38. Springer, Heidelberg (1995).  https://doi.org/10.1007/3-540-59496-5_286CrossRefGoogle Scholar
  30. 30.
    Chaitin, G.J.: The Unknowable. Springer Science & Business Media, Heidelberg (1999)MATHGoogle Scholar
  31. 31.
    Bennett, C.H., Gács, P., Li, M., Vitanyi, P., Zurek, W.H.: Information distance. arXiv preprint arXiv:1006.3520 (2010)
  32. 32.
    Calude, C.S.: Algorithmic randomness, quantum physics, and incompleteness. In: Margenstern, M. (ed.) MCU 2004. LNCS, vol. 3354, pp. 1–17. Springer, Heidelberg (2005).  https://doi.org/10.1007/978-3-540-31834-7_1CrossRefGoogle Scholar
  33. 33.
    Ming, L., Vitányi, P.M.: Kolmogorov complexity and its applications. Algorithms Complex. 1, 187 (2014)MATHGoogle Scholar
  34. 34.
    Vitányi, P.M., Li, M.: Minimum description length induction, Bayesianism, and Kolmogorov complexity. IEEE Trans. Inf. Theory 46(2), 446–464 (2000)MathSciNetCrossRefGoogle Scholar
  35. 35.
    Wallace, C.S., Dowe, D.L.: Minimum message length and Kolmogorov complexity. Comput. J. 42(4), 270–283 (1999)CrossRefGoogle Scholar
  36. 36.
    Muller, G.B., Wagner, G.P.: Novelty in evolution: restructuring the concept. Ann. Rev. Ecol. Syst. 22(1), 229–256 (1991)CrossRefGoogle Scholar
  37. 37.
    Pigliucci, M.: What, if anything, is an evolutionary novelty? Philos. Sci. 75(5), 887–898 (2008)CrossRefGoogle Scholar
  38. 38.
    Li, X., Croft, W.B.: An information-pattern-based approach to novelty detection. Inf. Process. Manag. 44(3), 1159–1188 (2008)CrossRefGoogle Scholar
  39. 39.
    Zhao, L., Zhang, M., Ma, S.: The nature of novelty detection. Inf. Retr. 9(5), 521–541 (2006)CrossRefGoogle Scholar
  40. 40.
    Kowaliw, T., Dorin, A., McCormack, J.: An empirical exploration of a definition of creative novelty for generative art. In: Korb, K., Randall, M., Hendtlass, T. (eds.) ACAL 2009. LNCS (LNAI), vol. 5865, pp. 1–10. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-10427-5_1CrossRefGoogle Scholar
  41. 41.
    Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41(3), 15 (2009)CrossRefGoogle Scholar
  42. 42.
    Venkatasubramanian, V., Rengaswamy, R., Yin, K., Kavuri, S.N.: A review of process fault detection and diagnosis: part I: quantitative model-based methods. Comput. Chem. Eng. 27(3), 293–311 (2003)CrossRefGoogle Scholar
  43. 43.
    Hodge, V., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85–126 (2004)CrossRefGoogle Scholar
  44. 44.
    Pimentel, M.A., Clifton, D.A., Clifton, L., Tarassenko, L.: A review of novelty detection. Sig. Process. 99, 215–249 (2014)CrossRefGoogle Scholar
  45. 45.
    Reed, R., Marks, R.J.: Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks. MIT Press, Cambridge (1999)Google Scholar
  46. 46.
    Thompson, B.B., Marks, R.J., Choi, J.J., El-Sharkawi, M.A., Huang, M.Y., Bunje, C.: Implicit learning in autoencoder novelty assessment. In: 2002 Proceedings of the 2002 International Joint Conference on Neural Networks, IJCNN 2002, vol. 3, pp. 2878–2883. IEEE (2002)Google Scholar
  47. 47.
    Lehman, J., Stanley, K.O.: Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19(2), 189–223 (2011)CrossRefGoogle Scholar
  48. 48.
    Mouret, J.B.: Novelty-based multiobjectivization. In: Doncieux, S., Bredèche, N., Mouret, J.B. (eds.) New Horizons in Evolutionary Robotics. SCI, vol. 341, pp. 139–154. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-18272-3_10CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringBaylor UniversityWacoUSA

Personalised recommendations