Skip to main content

Understanding Complex Systems: What Can the Speaking Lion Tell us?

  • Conference paper
The Biology and Technology of Intelligent Autonomous Agents

Part of the book series: NATO ASI Series ((NATO ASI F,volume 144))

Abstract

The rebirth of complex systems in several distinct domains of research has posed new epistemic questions. Self-organizing systems as well as autonomous robots have a tendency to not only behave in an unpredictable way, they are also extremely difficult to analyse. In this paper we discuss three problems with neural networks that are important for complex systems in general. They are related to the proper design of a self-organizing system, to the role of the system engineer, and to the proper explanation of system behavior. We present a generally applicable solutions, which is based on a “symbol grounding” neural network architecture. We also take a look at an implemented network which hints at the fact that grounding in this case must involve teleological terms. We then discuss the relation of this approach to the measurement problem in physics and point out similarities to existing positions in philosophy. However, it should be noted that our “solution” of the explanation problem may be judged as being a very sceptic one.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bertalanffy L. von: The Theory of Open Systems in Physics and Biology. Science, 111 (1950), pp. 23 ff

    Google Scholar 

  2. Braitenberg V.: Vehicles. Experiments in Synthetic Psychology, MIT Press, Cambridge, MA (1984)

    Google Scholar 

  3. Brooks R.A.: Elephants Don’t Play Chess, in Maes P. (ed.), Designing Autonomous Agents, MIT Press, Cambridge, MA, Bradford Books (I960) pp. 3–16

    Google Scholar 

  4. Brooks R.A.: Intelligence without Reason, in Proceedings of the 12th International Conference on Artificial Intelligence, Morgan Kaufmann, San Mateo, CA (1991) pp. 569–595

    Google Scholar 

  5. Cariani P.: Implications from Structural Evolution: Semantic Adaptation, in Caudill M. (ed.), Proceedings of the International Joint Conference on Neural Networks (Winter Meeting), Washington D.C., Lawrence Erlbaum, Hillsdale, NJ (1990) pp. 47–50

    Google Scholar 

  6. Diederich J.: Explanation and Neural Computation, GMD, Nr. 458 (1990)

    Google Scholar 

  7. Dorffner G., Prem E.: Connectionism, symbol grounding, and autonomous agents, Proceedings of the 15th Annual Meeting of the Cognitive Science Society, Boulder, CO (1993) pp. 144–148

    Google Scholar 

  8. Dreyfus H.L.: What Computers can’t do. A critique of artificial reason, Harper; Row, New York (1972)

    Google Scholar 

  9. Elman J.L.: Finding structure in time, Cognitive Science 14 (1990) pp. 179–211

    Article  Google Scholar 

  10. Harnad S.: The symbol grounding problem, Physica D, 42 (1990), pp. 335–346

    Article  Google Scholar 

  11. Harnad S.: Lost in the hermeneutic hall of mirrors, JETAI Journal of Experimental and Theoretical Artificial Intelligence 2 (1990) pp. 321–327

    Article  Google Scholar 

  12. Kohonen T.: Self–organized formation of topologically correct feature maps, in Anderson J.A. (ed.), Neurocompitting, A Bradford Book, MIT Press, Cambridge, MA (1988) pp. 511–522

    Google Scholar 

  13. Kripke S.: Wittgenstein on rules and private language, Harvard University Press, Cambridge, MA (1982)

    Google Scholar 

  14. Kugler P.N., Turvey M.T.: Information natural law and the self–assembly of rhythmic movement, Lawrence Erlbaum, Hillsdale, NJ (1987)

    Google Scholar 

  15. Kugler P.N., Turvey M.T.: Self–Organization, flow fields, and information, in Kugler P.N., Turvey M.T. (eds.), Selforganization in biological work spaces, North– Holland, Amsterdam (1989) pp. 1–33

    Google Scholar 

  16. Lange O.: Wholes and parts. A general theory of system behaviour, Pergamon, PWN–Polish Scientific Publishers, Oxford (Warszawa 1962 ), 1965

    Google Scholar 

  17. Lischka C.: Ueber die Blindheit des Wissensingenieurs, die Geworfenheit kognitiver Systeme und anderes…, KI 4 (1987) pp. 15–19

    Google Scholar 

  18. Partridge D.: What’s wrong with neural architectures, Computer Science Dept., Univ. of Exeter, Research Report 142 (1987)

    Google Scholar 

  19. Pask G.: Physical analogues to the growth of a concept, Mechanization of thought processes: Proc. of a symposium, National Physical Laboratories, November 1958, HMSO, London

    Google Scholar 

  20. Pask G.: An approach to cybernetics, Hutchinson, London (1961)

    Google Scholar 

  21. Pat tee H.H.: Universal principles of measurement and language functions in evolving systems, in Casti J.L., Karlqvist A. (eds.), Complexity, language and life: Mathematical approaches, Springer–Verlag, Berlin (1986) pp. 268–291

    Chapter  Google Scholar 

  22. Pattee H.H.: The measurement problem in physics, computation, and brain theories, in Carvallo M.E. (ed.), Nature, cognition and system II–current systems– scientific research on natural and cognitive systems, Vol. 2: On complementarity and beyond, Kluwer, Dordrecht (1992) pp. 197–192

    Google Scholar 

  23. Perlis D.: How can a program mean in Proceedings of the 10th International Joint Conference on Artificial Intelligence (IJCAI–87), Morgan Kaufmann, Los Altos, CA (1987) pp. 163–166

    Google Scholar 

  24. Prem E.: Aspects of rules and connectionisin, in Trappl R. (ed.), Cybernetics and Systems ‘92, World Scientific Publishing, Singapore (1992) pp. 1343–1350

    Google Scholar 

  25. Prem E.: Symbol Grounding: Die Bedeutung der Verankerung von Symbolen in reichhaltiger sensorischer Erfahrung mittels neuronalen Netzen, PhD Thesis, Uni–versity of Technology, Wien, Austria, 1994

    Google Scholar 

  26. Rosen R.: Fundamentals of measurement and representation of natural systems, North–Holland, New York, 1978

    Google Scholar 

  27. Sejnowski T.J., Rosenberg C.R.: Parallel networks that learn to pronounce english text, Complex Systems, 1 (1987) pp. 145–168

    MATH  Google Scholar 

  28. Smithers T.: Taking eliminative materialism seriously: A methodology for autonomous systems research, in: Varela F.J.., Towards a practice of autonomous systems (1991) pp. 31–40

    Google Scholar 

  29. Wittgenstein L.: Philosophische Untersuchungen, Suhrkainp, Frankfurt/Main, Werkausgabe Bd. l (1986), 1953

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Prem, E. (1995). Understanding Complex Systems: What Can the Speaking Lion Tell us?. In: Steels, L. (eds) The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series, vol 144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79629-6_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-79629-6_22

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-79631-9

  • Online ISBN: 978-3-642-79629-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics