An Analysis of the Effects of Lifetime Learning on Population Fitness and Diversity in an NK Fitness Landscape

  • Dara Curran
  • Colm O’Riordan
  • Humphrey Sorensen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4648)


This paper examines the effects of lifetime learning on the diversity and fitness of a population. Our experiments measure the phenotypic diversity of populations evolving by purely genetic means (population learning) and of others employing both population learning and lifetime learning. The results obtained show, as in previous work, that the addition of lifetime learning results in higher levels of fitness than population learning alone. More significantly, results from the diversity measure show that lifetime learning is capable of sustaining higher levels of diversity than population learning alone.


Diversity Measure Bias Direction Learning Cycle Neural Network Ensemble Weak Individual 
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.
    Hinton, G.E., Nowlan, S.J.: How learning guides evolution. Complex Systems 1, 495–502 (1987)zbMATHGoogle Scholar
  2. 2.
    Nolfi, S., Parisi, D.: Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior 5(1), 75–97 (1996)CrossRefGoogle Scholar
  3. 3.
    Floreano, D., Mondada, F.: Evolution of plastic neurocontrollers for situated agents. In: Animals to Animats, vol. 4 (1996)Google Scholar
  4. 4.
    Sasaki, T., Tokoro, M.: Adaptation toward changing environments: Why darwinian in nature? In: Husbands, P., Harvey, I. (eds.) Fourth European Conference on Artificial Life, pp. 145–153. MIT Press, Cambridge (1997)Google Scholar
  5. 5.
    Pereira, F.B., Costa, E.: How learning improves the performance of evolutionary agents: A case study with an information retrieval system for a distributed environment. In: Proceedings of the International Symposium on Adaptive Systems: Evolutionary Computation and Probabilistic Graphical Models (ISAS 2001), pp. 19–23 (2001)Google Scholar
  6. 6.
    Watson, J., Wiles, J.: The rise and fall of learning: A neural network model of the genetic assimilation of acquired traits. In: Proceedings of the 2002 Congress on Evolutionary Computation (CEC 2002), pp. 600–605 (2002)Google Scholar
  7. 7.
    Curran, D., O’Riordan, C.: On the design of an artificial life simulator. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2773, pp. 549–555. Springer, Heidelberg (2003)Google Scholar
  8. 8.
    Curran, D., O’Riordan, C.: Artificial life simulation using marker based encoding. In: Proceedings of the 2003 International Conference on Artificial Intelligence (IC-AI 2003), vol. II., Las Vegas, Nevada, USA, pp. 665–668 (2003)Google Scholar
  9. 9.
    Mayley, G.: Guiding or hiding: Explorations into the effects of learning on the rate of evolution. In: Proceedings of the Fourth European Conference on Artificial Life, MIT Press, Cambridge (1997)Google Scholar
  10. 10.
    O’Reilly, U.M.: Using a distance metric on genetic programs to understand genetic operators. In: IEEEInternational Conference on Systems, Man, and Cybernetics, vol. 5, pp. 4092–4097. IEEE Computer Society Press, Los Alamitos (1997)Google Scholar
  11. 11.
    De Jong, K.A.: Analysis of Behavior of a Class of Genetic Adaptive Systems. PhD thesis, The University of Michigan (1975)Google Scholar
  12. 12.
    Booker, L.B.: Improving the performance of genetic algorithms in classifier systems. In: Proc. of the International Conference on Genetic Algorithms and Their Applications, Pittsburgh, PA, pp. 80–92 (1985)Google Scholar
  13. 13.
    Collins, R.J., Jefferson, D.R.: Selection in massively parallel genetic algorithms. In: ICGA, pp. 249–256 (1991)Google Scholar
  14. 14.
    Darwin, C.: The Origin of Species: By Means of Natural Selection or the Preservation of Favoured Races in the Struggle for Life. Bantam Press, London (1859)Google Scholar
  15. 15.
    Baldwin, J.M.: A new factor in evolution. American Naturalist 30, 441–451 (1896)CrossRefGoogle Scholar
  16. 16.
    Lamarck, J.B.: Philosophie Zoologique. Chez Dentu, Paris (1809)Google Scholar
  17. 17.
    Boers, E., Borst, M., Sprinkhuizen-Kuyper, I.: Evolving Artificial Neural Networks using the “Baldwin Effect”. Technical Report TR 95-14 (1995)Google Scholar
  18. 18.
    Turney, P.D.: How to shift bias: Lessons from the baldwin effect. Evolutionary Computation 4(3), 271–295 (1996)Google Scholar
  19. 19.
    Suzuki, R., Arita, T.: The baldwin effect revisited: Three steps characterized by the quantitative evolution of phenotypic plasticity. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 395–404. Springer, Heidelberg (2003)Google Scholar
  20. 20.
    Arita, T., Suzuki, R.: Interactions between learning and evolution: The outstanding strategy generated by the baldwin effect. In: Proceedings of Artificial Life VII, pp. 196–205. MIT Press, Cambridge (2000)Google Scholar
  21. 21.
    Liu, Y., Yao, X., Higuchi, T.: Evolutionary ensembles with negative correlation learning. IEEE Transactions on Evolutionary Computation 4(4), 380–387 (2000)CrossRefGoogle Scholar
  22. 22.
    Opitz, D.W., Shavlik, J.W.: Generating accurate and diverse members of a neural-network ensemble. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 535–541. MIT Press, Cambridge (1996)Google Scholar
  23. 23.
    Brown, G.: Diversity in Neural Network Ensembles. PhD thesis, University of Birmingham (2003)Google Scholar
  24. 24.
    Burke, E.K., Gustafson, S., Kendall, G.: Diversity in genetic programming: an analysis of measures and correlation with fitness. IEEE Trans. Evolutionary Computation 8(1), 47–62 (2004)CrossRefGoogle Scholar
  25. 25.
    Eriksson, R.I.: An initial analysis of the ability of learning to maintain diversity during incremental evolution. In: Freitas, A.A., Hart, W., Krasnogor, N., Smith, J. (eds.) Data Mining with Evolutionary Algorithms, Las Vegas, Nevada, USA, pp. 120–124 (2000),
  26. 26.
    Curran, D., O’Riordan, C.: Increasing population diversity through cultural learning. Adaptive Behavior 14(4) (2006)Google Scholar
  27. 27.
    Kaufmann, S.A.: Adaptation on rugged fitness landscapes. Lectures in the Sciences of Complexity 1, 527–618 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Dara Curran
    • 1
  • Colm O’Riordan
    • 2
  • Humphrey Sorensen
    • 1
  1. 1.Dept. of Computer Science, University College Cork, Ireland 
  2. 2.Dept. of Information Technology, National University of Ireland, Galway 

Personalised recommendations