The Cognitive Development of an Autonomous Behaving Artifact: The Self-Organization of Categorization, Sequencing, and Chunking

  • Paul F. M. J. Verschure
Part of the Studies in Cognitive Systems book series (COGS, volume 26)


Within the context of the debate between computationalist and association-ist approaches towards understanding the mind, brain, and behavior a self-organizing model is proposed that can acquire representations of its interaction with the world and derive higher-level representations of these categorizations by means of sequencing and chunking. The model illustrates the properties of an integrated synthetic approach towards modeling behavior based on the notion of convergent validation. The design decisions behind the presented model are made explicit in terms of considerations on the nature of the interaction between an autonomously behaving system and its environment. The results are interpreted towards issues in the domain of cognitive science, psychology, and neurobiology. In addition the progress of the program proposed in this chapter over the last 6 years will be evaluated.


Adaptive Control Convergent Validation Control Structure Unconditioned Response Command Neuron 
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. Almassy, N. (1993). Bugworld: A distributed environment for the development of control architectures in multi-agent worlds. Technical Report 93.32. University of Zurich: Institute of Informatics.Google Scholar
  2. Almassy, N., & P.F.M.J. Verschure (1992). Optimizing self-organizing control architectures with genetic algorithms: The interaction between natural selection and ontogenesis. In R. Manner & B. Manderick (eds.), Proceedings of the Second Conference on Parallel Problem Solving from Nature (pp. 451–460).Google Scholar
  3. Brooks, R. (1986). A robust layered control system for a mobile robot. IEEE: Journal of Robotics and Automation 2, 14–23.MathSciNetCrossRefGoogle Scholar
  4. Brooks, R. (1991). Intelligence without representation. Artificial Intelligence 47, 139–159.CrossRefGoogle Scholar
  5. Chomsky, N. (1959). A review of B. F. Skinner’s verbal behavior. Language 35, 26–58.CrossRefGoogle Scholar
  6. Clancey, W. (1989). The frame of reference problem in cognitive modeling. Proceedings of the Annual Conference of the Cognitive Science Society (pp. 107–114). Hillsdale, NJ: Erlbaum Ass.Google Scholar
  7. Clancey, W. (1996). Situated cognition: On human knowledge and computer representations. Cambridge, England: Cambridge University Press.Google Scholar
  8. Edelman, G., G. Reeke, W. Gall, G. Tononi, D. Williams, & O. Sporns (1992). Synthetic neural modeling applied to a real-world artifact. Proceedings of the National Academy of Sciences of the USA 89, 7267–7271.CrossRefGoogle Scholar
  9. Farmer, J.D. (1990). A Rosetta stone for connectionism. Physica D 42, 153–187.MathSciNetGoogle Scholar
  10. Fodor, J. (1983). The modularity of mind. Cambridge, MA: MIT Press.Google Scholar
  11. Friston, K.J., G. Tononi, G. Reeke, O. Sporns, & G.M. Edelman (1994). Value-dependent selection in the brain: Simulation in a synthetic neural model. Neuroscience 59(2), 229–243.CrossRefGoogle Scholar
  12. Gardner, H. (1987). The mind’s new science: A history of the cognitive revolution. New York: Basic Books.Google Scholar
  13. Goldstein, L., & K. Smith (1991). Bugworld: A distributed environment for the study of multi-agent learning algorithms. Technical report, Department of Computer Science, University of California, Santa Clara, CA.Google Scholar
  14. Hendriks-Jansen, H. (1996). Catching ourselves in the act. Cambridge, MA: MIT Press.Google Scholar
  15. Holland, J.H. (1975). Adaptation in natural and artificial systems. Ann Arbor, MI: University of Michigan Press.Google Scholar
  16. Indeveri, G., & P.F.M.J. Verschure (1997). Autonomous vehicle guidance using analog VLSI neuromorphic sensors. In W. Gerstner, A. Germond, & J.-D. Nicoud (eds.), Proceedings Artificial Neural Networks-ICANN97 (Lausanne, Switzerland). Lecture Notes in Computer Science (pp. 811–816). Berlin: Springer.Google Scholar
  17. Klopf, A. (1982). The hedonistic neuron: A theory of memory, learning and intelligence. Washington, DC: Hemisphere.Google Scholar
  18. Kupfermann, I., & K.R. Weiss (1978). The command neuron concept. Behavioral and Brain Sciences 1(1), 3–39.CrossRefGoogle Scholar
  19. McCarthy, J., & P.J. Hayes (1969). Some philosophical problems from the standpoint of artificial intelligence. Machine Intelligence 4, 463–502.MATHGoogle Scholar
  20. McFarland, D., & T. Bösser (1993). Intelligent behavior in animals and robots. Cambridge, MA: MIT Press.Google Scholar
  21. Mondada, F., & P.F.M.J. Verschure (1993). Modeling system-environment interaction: The complementary roles of simulations and real world artifacts. Proceedings of the Second European Conference on Artificial Life (pp. 808–817). Cambridge, MA: MIT Press.Google Scholar
  22. Moore, M.E. (1956). Gedanken-experiments on sequential machines. In C.E. Shannon & J. McCarthy (eds.), Automata Studies (pp. 129–153). Princeton, NJ: Princeton University Press.Google Scholar
  23. Newell, A. (1990). Unified theories of cognition. Cambridge, MA: Harvard University Press.Google Scholar
  24. Omidvar, O., & P. Van der Smagt (1997). Neural systems for robotics. New York: Academic Press.Google Scholar
  25. Pfeiler, R. (1995). Cognition: Perspectives from autonomous agents. Robotics and Autonomous Systems 15, 47–70.CrossRefGoogle Scholar
  26. Pfeifer, R., & C. Scheier (1999). Understanding Intelligence. Cambridge, MA: MIT Press.Google Scholar
  27. Piaget, J. (1963). The psychology of intelligence. Paterson, NJ: Littlefield, Adams &Co.Google Scholar
  28. Rumelhart, D., J. McClelland, & the PDP Research Group (1986). Parallel distributed processing: Explorations in the microstructure of cognition. Cambridge, MA: MIT Press.Google Scholar
  29. Suchman, L.A. (1987). Plans and situated actions. Cambridge, England: Cambridge University Press.Google Scholar
  30. Sutton, R.S., & A.G. Barto (1981). Toward a modern theory of adaptive networks: expectations and prediction. Psychological Review 88, 135–170.CrossRefGoogle Scholar
  31. Verschure, P.F.M.J. (1990). Smolensky’s theory of mind. Behavioral and Brain Sciences 13, 407.CrossRefGoogle Scholar
  32. Verschure, P.F.M.J. (1992). Taking connectionism seriously: The vague promise of subsymbolism and an alternative. Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society (Bloomington, Indiana) (pp. 653–658). Hillsdale, NJ: Erlbaum Ass.Google Scholar
  33. Verschure, P.F.M.J. (1993). Formal minds and biological brains. IEEE expert 8(5), 66–75.CrossRefGoogle Scholar
  34. Verschure, P.F.M.J. (1997). Connectionist explanation: Taking positions in the mind-brain dilemma. In G. Dorffner (ed.), Neural networks and a new artificial intelligence (pp. 133–188). London: Thompson. (First presented at ZiF workshop Mind and Brain, 1990.)Google Scholar
  35. Verschure, P.F.M.J. (1998). Synthetic epistemology: The acquisition, retention, and expression of knowledge in natural and synthetic systems. Proceedings World Conference on Computational Intelligence (Anchorage), (pp. 147–153). IEEE.Google Scholar
  36. Verschure, P.F.M.J., & A.C.C. Coolen (1991). Adaptive fields: Distributed representations of classically conditioned associations. Network 2, 189–206.CrossRefGoogle Scholar
  37. Verschure, P.F.M.J., & P. König (1997). Modulation of temporal interactions in cortical circuits. In H.-M. Gross (ed.), Proceedings of the Conference on Selbstorganisation von adaptivem Verhalten (SOAVE97), (pp. 77–88). Düsseldorf, Germany: DVI.Google Scholar
  38. Verschure, P.F.M.J., & P. König (1998). On the role of biophysical properties of cortical neurons in binding and segmentation of visual scenes. Neural Computation 11, 1113–1138.CrossRefGoogle Scholar
  39. Verschure, P.F.M.J., B. Kröse, & R. Pfeifer (1992). Distributed adaptive control: The self-organization of structured behavior. Robotics and Autonomous Systems 9, 181–196.CrossRefGoogle Scholar
  40. Verschure, P.F.M.J., & R. Pfeifer (1992). Categorization, representations, and the dynamics of system-environment interaction: A case study in autonomous systems. In J.A. Meyer, H. Roitblat, & S. Wilson (eds.), From animals to animats: Proceedings of the Second International Conference on Simulation of Adaptive behavior (Honolulu, Hawaii), (pp. 210–217). Cambridge, MA: MIT Press.Google Scholar
  41. Verschure, P.F.M.J., & T. Voegtlin (1998a). A bottom-up approach towards the acquisition, retention, and expression of sequential representations: Distributed adaptive control III. Neural Networks 11, 1531–1549.CrossRefGoogle Scholar
  42. Verschure, P.F.M.J., & T. Voegtlin (1998b). A comparative analysis of different levels of behavioral control applied to a behaving device: Performance, stimulus sampling, and stage transitions. Submitted for publication.Google Scholar
  43. Verschure, P.F.M.J., J. Wray, O. Sporns, G. Tononi, & G. Edelman (1995). Multilevel analysis of classical conditioning in a behaving real world artifact. Robotics and Autonomous Systems 16, 247–265.CrossRefGoogle Scholar
  44. Vinkhuyzen, R., & P.F.M.J. Verschure (1994). The legacy of Allen Newell: Unified theories of cognition. American Journal of Psychology 107(3), 454–464.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2000

Authors and Affiliations

  • Paul F. M. J. Verschure
    • 1
  1. 1.Institut für Neuroinformatik, Eidgenössische Technische HochschuleUniversität ZürichSwitzerland

Personalised recommendations