Searching for Emergent Representations in Evolved Dynamical Systems

  • Thomas Hope
  • Ivilin Stoianov
  • Marco Zorzi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)


This paper reports an experiment in which artificial foraging agents with dynamic, recurrent neural network architectures, are "evolved" within a simulated ecosystem. The resultant agents can compare different food values to "go for more," and display similar comparison performance to that found in biological subjects. We propose and apply a novel methodology for analysing these networks, seeking to recover their quantity representations within an Approximationist framework. We focus on Localist representation, seeking to interpret single units as conveying representative information through their average activities. One unit is identified that passes our "representation test", representing quantity by inverse accumulation.


Food Group Hide Unit Food Quantity Numerical Distance Functional Decomposition 
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.


  1. 1.
    Feyerabend, P.: Materialism and the mind-body problem. Review of Mataphysics 17, 49–66 (1963)Google Scholar
  2. 2.
    Feyerabend, P.: Mental events and the brain. Journal of Philosophy 60, 295–296 (1963)CrossRefGoogle Scholar
  3. 3.
    Stich, S., Ravenscroft, I.: What is Folk Psychology? Cognition 50, 447–468 (1994)CrossRefGoogle Scholar
  4. 4.
    Rorty, R.: Mind-Body Identity, Privacy, and Categories. Review of Metaphysics 19, 24–54 (1965)Google Scholar
  5. 5.
    Crowther-Heyk, H.: George Miller, language, and the computer metaphor. History of Psychology 2, 37–64 (1999)CrossRefGoogle Scholar
  6. 6.
    Bechtel, W., Richardson, R.C.: Discovering complexity: Decomposition and localization as strategies in scientific research, ch. 2. Princeton University Press, Princeton (1993)Google Scholar
  7. 7.
    Stoianov, I., Zorzi, M., Umiltà, C.: The role of semantic and symbolic representations in arithmetic processing: Insights from simulated discalculia in a connectionist model. Cortex 40, 194–196 (2004)CrossRefGoogle Scholar
  8. 8.
    Brooks, R.A.: Intelligence without representation. Artificial Intelligence 47, 139–159 (1991)CrossRefGoogle Scholar
  9. 9.
    Beer, R.D.: Dynamical approaches to cognitive science. Trends in Cognitive Sciences 4(3), 91–99 (2000)CrossRefMathSciNetGoogle Scholar
  10. 10.
    van Gelder, T.J.: Dynamic approaches to cognition. In: Wilson, R., Keil, F. (eds.) The MIT Encyclopedia of Cognitive Sciences, pp. 244–246. MIT Press, Cambridge (1999)Google Scholar
  11. 11.
    Harvey, I.: Untimed and misrepresented: Connectionism and the computer metaphor. Newsletter of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB Quarterly) 96, 20–27 (1996)Google Scholar
  12. 12.
    Cabeza, R., Nyberg, L.: Imaging cognition II: an empirical review of 275 PET and fMRI Studies. Journal of Cognitive Neuroscience 12, 1–47 (2000)CrossRefGoogle Scholar
  13. 13.
    Zorzi, M., Stoianov, I., Umiltà, C.: Computational modeling of numerical cognition. In: Campbell, J. (ed.) Handbook of mathematical cognition, ch. 5, pp. 67–83. Psychology Press, London (2005)Google Scholar
  14. 14.
    Dahaene, S., Cohen, L., Sigman, M., Vinckier, F.: The neural code for written words: a proposal. Trends in Cognitive Science 9(7), 335–341 (2005)CrossRefGoogle Scholar
  15. 15.
    Naccache, L., Dahaene, S.: The priming method: imaging unconscious repetition priming reveals an abstract representation of number in the parietal lobes. Cerebral Cortex 11, 966–974 (2001)CrossRefGoogle Scholar
  16. 16.
    Smolensky, P.: On Variable Binding and the Representation of Symbolic Structures in Connectionist Systems. Technical report CU-CS-355-87, Department of Computer Science, University of Colorado at Boulder (1987)Google Scholar
  17. 17.
    Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: Maes, P., Mataric, M., Meyer, J., Pollack, J., Wilson, S. (eds.) Proceedings of the 4th International Conference on Simulation of Adaptive Behavior, pp. 421–429. MIT Press, Cambridge (1996)Google Scholar
  18. 18.
    Verguts, T., Fias, W.: Representation of number in animals and humans: a neural model. Journal of Cognitive Neuroscience 16(9) (2004)Google Scholar
  19. 19.
    Gelman, R., Gallistel, C.R.: Language and the origin of numerical concepts. Science 306(5695), 441–443 (2004)CrossRefGoogle Scholar
  20. 20.
    Butterworth, B.: What Counts, ch. 3, pp. 144–147. The Free Press, New York (1999)Google Scholar
  21. 21.
    Uller, C., Jaeger, R., Guidry, G., Martin, C.: Salamanders (Plethodon cinereus) go for more: rudiments of number in an amphibian. Animal Cognition 6, 105–112 (2003)Google Scholar
  22. 22.
    Watson, R.A., Pollack, J.B.: Coevolutionary Dynamics in a Minimal Substrate. In: Spector, L., et al. (eds.) Proceedings of the 2001 Genetic and Evolutionary Computation Conference. Morgan Kaufmann, San Francisco (2001)Google Scholar
  23. 23.
    Keinan, A., Sandbank, B., Hilgetag, C.C., Meilijson, I., Ruppin, E.: Fair attribution of functional contribution in artificial and biological networks. Neural Computation 16(9), 1887–1915 (2004)MATHCrossRefGoogle Scholar
  24. 24.
    Aharanov, R., Segev, L., Meilijson, I., Ruppin, E.: Localization of function via lesion analysis. Neural Computation 14(4), 885–913 (2003)CrossRefGoogle Scholar
  25. 25.
    Nieder, A., Freedman, D.J., Miller, E.K.: Representation of the quantity of visual items in the primate prefrontal corext. Science 6, 1708–1711 (2002)CrossRefGoogle Scholar
  26. 26.
    Meck, W.H., Church, R.M.: A mode control model of counting and timing processes. Journal of Experimental Psychology: Animal Behaviour Processes 9, 320–324 (1983)CrossRefGoogle Scholar
  27. 27.
    Tomko, G., Crapper, D.: Neuronal variability: non-stationary responses to identical visual stimuli. Brain Res. 79, 405–418 (1974)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Thomas Hope
    • 1
  • Ivilin Stoianov
    • 1
  • Marco Zorzi
    • 1
  1. 1.Computational Cognitive Neuroscience LabUniversity of PadovaPadovaItaly

Personalised recommendations