The Baldwin Effect Revisited: Three Steps Characterized by the Quantitative Evolution of Phenotypic Plasticity

  • Reiji Suzuki
  • Takaya Arita
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2801)


An interaction between evolution and learning called the Baldwin effect has been known for a century, but it is still poorly appreciated. This paper reports on a computational approach focusing on the quantitative evolution of phenotypic plasticity in complex environment so as to investigate its benefit and cost. For this purpose, we investigate the evolution of connection weights in a neural network under the assumption of epistatic interactions. Phenotypic plasticity is introduced into our model, in which whether each connection weight is plastic or not is genetically defined and connection weights with plasticity can be adjusted by learning. The simulation results have clearly shown that the evolutionary scenario consists of three steps characterized by transitions of the phenotypic plasticity and phenotypic variation, in contrast with the standard interpretation of the Baldwin effect that consists of two steps. We also conceptualize this evolutionary scenario by using a hill-climbing image of a population on a fitness landscape.


Phenotypic Variation Phenotypic Plasticity Epistatic Interaction Connection Weight Evolutionary Scenario 
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.
    Baldwin, J.M.: A New Factor in Evolution. American Naturalist 30, 441–451 (1896)CrossRefGoogle Scholar
  2. 2.
    Turney, P., Whitley, D., Anderson, R.W.: Evolution, Learning, and Instinct: 100 Years of the Baldwin Effect. Evolutionary Computation 4(3), 4–8 (1996)Google Scholar
  3. 3.
    Waddington, C.H.: Canalization of Development and the Inheritance of Acquired Characters. Nature 150, 563–565 (1942)CrossRefGoogle Scholar
  4. 4.
    Hinton, G.E., Nowlan, S.J.: How Learning Can Guide Evolution. Complex Systems 1, 495–502 (1987)zbMATHGoogle Scholar
  5. 5.
    Harvey, I.: The Puzzle of the Persistent Question Marks: A Case Study of Genetic Drift. In: Proceedings of the Fifth International Conference on Genetic Algorithms, pp. 15–22 (1993)Google Scholar
  6. 6.
    Watson, R.A., Pollack, J.B.: How Symbiosis Can Guide Evolution. In: Fifth European Conference on Artificial Life, pp. 29–38 (1999)Google Scholar
  7. 7.
    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 (2000)Google Scholar
  8. 8.
    Ackley, D., Littman, M.: Interaction between Learning and Evolution. In: Proceedings of Artificial Life II, pp. 487–509 (1991)Google Scholar
  9. 9.
    Parisi, D., Nolfi, S.: The Influence of Learning on Evolution. Adaptive Individuals in Evolving Populations, pp. 419–428 (1996)Google Scholar
  10. 10.
    Sasaki, T., Tokoro, M.: Evolving Learnable Neural Networks under Changing Environments with Various Rates of Inheritance of Acquired Characters: Comparison between Darwinian and Lamarckian Evolution. In: Artificial Life, vol. 5(3), pp. 203–223 (1999)Google Scholar
  11. 11.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Representations by Back-Propagating Errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  12. 12.
    Turney, P.: How to Shift Bias: Lessons from the Baldwin Effect. Evolutionary Computation 4(3), 271–295 (1996)CrossRefGoogle Scholar
  13. 13.
    DeWitt, T.J., Sih, A., Wilson, D.S.: Costs and Limits of Phenotypic Plasticity. Trends in Ecology and Evolution 13, 77–81 (1998)CrossRefGoogle Scholar
  14. 14.
    Mayley, G.: Landscapes, Learning Costs and Genetic Assimilation. Evolutionary Computation 4(3), 213–234 (1996)CrossRefGoogle Scholar
  15. 15.
    Provine, W.B.: Sewall Wright and Evolutionary Biology. The University of Chicago Press, Chicago (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Reiji Suzuki
    • 1
  • Takaya Arita
    • 1
  1. 1.Graduate School of Human InformaticsNagoya UniversityNagoyaJapan

Personalised recommendations