Does Complex Learning Require Complex Connectivity?

  • Carlos Rubén de la Mora-Basáñez
  • Alejandro Guerra-Hernández
  • Luc Steels
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4140)


Small World and Scale Free network properties characterize many real complex phenomena. We assume that low level connectivity with such topological properties, e.g., anatomical or functional connectivity in brains, is compulsory to achieve high level cognitive functionality, as language. The study of these network properties provides tools to approach different issues in behavior based Artificial Intelligence (AI) that usually have been ill defined, e.g., complexity and autonomy. In this paper, we propose a model in which situated agents evolve knowledge networks holding both Small World and Scale Free properties. Experimental results in the context of Pragmatic Games, elucidate some required conditions to obtain the expected network properties when performing complex learning.


Random Graph Degree Distribution Attentional Focus Small World Characteristic Path Length 
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.
    Albert, R., Jeong, H., Barabási, A.-L.: The diameter of the World Wide web. Nature 401, 130–131 (1999)CrossRefGoogle Scholar
  2. 2.
    Albert, R., Barabási, A.-L.: Statistical Mechanics of Complex Networks. Reviews of Modern Physics 74, 47 (2002)CrossRefMathSciNetMATHGoogle Scholar
  3. 3.
    Barabási, A.-L., Albert, R.: Emergence of scaling in random networks. Science 286, 509–512 (1999)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Barabási, A.-L.: Linked: The New Science of Networks. Perseus (2002)Google Scholar
  5. 5.
    Barabási, A.-L., et al.: On the topology of the scientific collaboration networks. Physica A 311, 590–614 (2002)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Brooks, R.A.: Cambrian Intelligence: The early history of the New AI. MIT Press, Cambridge (1999)MATHGoogle Scholar
  7. 7.
    Collier, J.: Autonomy and Process Closure as the basis for functionality. In: Chandler, J.L.R., Van der Vijver, G. (eds.) Annals of the New York Academy of Sciences, New York, USA, vol. 901, pp. 280–290 (2000)Google Scholar
  8. 8.
    de la Mora-Basáñez, C.R., Gesherson, C., García-Vega, V.A.: Representation development and behavior modifiers. In: Lemaître, C., Reyes, C.A., González, J.A. (eds.) IBERAMIA 2004. LNCS (LNAI), vol. 3315, pp. 504–513. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Dorner, D., Hille, K.: Artificial souls: Motivated emotional robots. In: IEEE Conference Proceedings, International Conference on Systems, Man, and Cybernetics; Intelligent Systems for the 21st Century, Vancouver, Canada, vol. 4, pp. 3828–3832 (1995)Google Scholar
  10. 10.
    Eguiluz, V.M., et al.: Scale-free brain functional networks. Phys. Rev. Letters 92, 018102 (2005)CrossRefGoogle Scholar
  11. 11.
    Ferrer-i-Cancho, R., Sole, R.V.: The small world of human language. Proceedings of The Royal Society of London, Series B, Biological Sciences 268(1482), 2261–2265 (2001)CrossRefGoogle Scholar
  12. 12.
    Jeong, H., et al.: The large-scale organization of metabolic networks. Nature 407, 651–654 (2000)CrossRefGoogle Scholar
  13. 13.
    Lederberg, J.: The Meaning of Epigenetics. The Scientist 15(18), 6 (2001)Google Scholar
  14. 14.
    Levenson, J.M., Sweatt, D.: Epigenetic mechanisms in memory formation. Nature 6, 109–119 (2005)Google Scholar
  15. 15.
    Mcintyre, A., Kaplan, F., Steels, L.: Crucial Factors in the Origins of Word- Meaning. In: Wray, A. (ed.) The Transition to Language, pp. 252–271. Oxford University Press, Oxford (2002)Google Scholar
  16. 16.
    Milo, R., et al.: Network Motifs: Simple Building Blocks of Complex Networks. Science 298, 824–827 (2002)CrossRefGoogle Scholar
  17. 17.
    Milo, R., et al.: Superfamilies of evolved and Designed Networks. Science 303, 1538–1542 (2004)CrossRefGoogle Scholar
  18. 18.
    Newman, M.E.J.: The structure and function of complex networks. SIAM Review 45(2), 167–256 (2003)MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Prince, C.G.: Introduction: The Second International Workshop on Epigenetic Robotics, Lund University Cognitive Studies 94, Lund, Sweden (2002)Google Scholar
  20. 20.
    Scheutz, M.: The Evolution of Simple Affective States in Multi-Agent Environments. In: Proceedings of AAAI Fall Symposium 2001. AAAI Press, USA (2001)Google Scholar
  21. 21.
    Smithers, T.: Taking Eliminative Materialism Seriously: A Methodology for Autonomous Systems Research. In: Varela, F.J., Bourgine, P. (eds.) Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, pp. 31–40. MIT Press/Bradford Book (1992)Google Scholar
  22. 22.
    Sole, R.V., et al.: Language Networks: their structure, function and evolution, Santa Fe Institute Working Paper 05-12-042, Santa Fe, CA., USA (2006)Google Scholar
  23. 23.
    Steels, L., Brooks, R.: The Artificial Life route to Artificial Intelligence: Building situated embodied agents. Lawrence Erlbaum Ass. (1995)Google Scholar
  24. 24.
    Steels, L.: Self-organizing vocabularies. In: Langton, V.C., Shimohara, T. (eds.) Proceedings of Alife, Nara Japan, pp. 179–184 (1996)Google Scholar
  25. 25.
    Sporns, O., et al.: Organization, development and function of complex brain networks. Trends in Cognitive Sciences 8, 418–425 (2004)CrossRefGoogle Scholar
  26. 26.
    Watts, D.: Small-Worlds. The dynamics of networks between order and randomness. Princeton Studies in Complexity. Princeton University Press, USA (1999)Google Scholar
  27. 27.
    Ziemke, T.: Are Robots Embodied? In: Proceedings of the First International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Lund University Cognitive Studies 85 Lund, Sweden (2001)Google Scholar
  28. 28.
    Zlatev, J., Balkenius, C.: Introduction: Why ’epigenteic robotics’? In: Proceedings of the First International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Lund University Cognitive Studies 85, Lund, Sweden, pp. 1–4 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Carlos Rubén de la Mora-Basáñez
    • 1
    • 2
  • Alejandro Guerra-Hernández
    • 1
  • Luc Steels
    • 2
  1. 1.Departamento de Inteligencia ArtificialUniversidad Veracruzana, Facultad de Física e Inteligencia ArtificialXalapa, Ver.México
  2. 2.Artificial Intelligence LaboratoryVrije Universiteit BrusselBrusselsBelgium

Personalised recommendations