Skip to main content
SpringerLink
Log in

Self-organization in computational systems: Advance of a new computational paradigm?

  • Conference paper
  • First Online:
Parallelism, Learning, Evolution (WOPPLOT 1989)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 565))

Included in the following conference series:

  • 163 Accesses

Abstract

To summarize, we should like to give some (doubtful?) answers to some (doubtful?) questions:

What are Neural Networks?

  • the omnipotent medicine for solving AI-problems or

  • just a new paradigm for information processing

What is evolution?

  • the omnipotent medicine for curing neural network shortcomings or diseases or

  • just a new paradigm for tuning system parameters according to some optimization function or

  • discovering new mechanisms or “frames of effect”, i.e. a set of meta-rules for meta-programming, hoping that the cardinality of that set of meta-rules is less than the cardinality of the set of common program writing rules.

What is the governing principle behind evolution?

  • selection of the fittest in a hostile environment or

  • an optimistic force driven from within living beings (“new biology”; cf. MÜhlenbein's contribution to this volume).

What is self-organization?

  • just a new gap-filler for unexplicable phenomena in systems.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agha, G., Hewitt, C.: Concurrent Programming Using Actors-Exploiting Large-Scale Parallelism, Fifth Conference on Foundations of Software Technology and Theoretical Computer Science, Springer Verlag 1985, S.19 Zit. nach: Informatik-Spektrum, Bd.10, Heft 1, Febr. 1987, S.43

    Google Scholar 

  2. Babb II, R.G.: Parallel Processing with Large-Grain Data Flow Techniques, IEEE Computer, July 1984, S.55–61

    Google Scholar 

  3. DARPA Neural Network Study (October 1987–February 1988), AFCEA International Press

    Google Scholar 

  4. Dennis, J.B., Misunas, D.P.: A Computer Architecture for Highly Parallel Signal Processing, ACM Proceedings of the 1974 National Conference, New York, Nov. 1974, S.402–409

    Google Scholar 

  5. Dennis, J.B.: The Varieties of Data Flow Computers, 1th International Conference on Distributed Computing Systems, Euntsville/Alabama, Oct. 1979, S.430–439

    Google Scholar 

  6. Dennis, J.B.: Data Flow Supercomputers, Computer, Nov.1980, S.48–56

    Google Scholar 

  7. Dennis, J.B., Gao, G.-R., Todd, K.W.: Modeling the Weather with a Data Flow Supercomputer, IEEE Transactions on Computers, Vol.C-33, No.7, July 1984, S.592–603

    Google Scholar 

  8. Goldberg, A., Robson, D., Ingalls, D.: SMALLTALK-80: The Language and its Interpretation SMALLTALK-80: The Interactive Programming Environment, Edison-Wesley, Reading/Mass., 1983

    Google Scholar 

  9. Hoare, C.A.R.: Communicating Sequential Processes Communications of the ACM, Vol.21, Aug. 1978, S.666–677

    Google Scholar 

  10. Hull, M.E.: Implementations of the CSP Notation for Concurrent Systems, The Computer Journal, Vol.29, No.6, 1986 S.500–505

    Google Scholar 

  11. Linsker, R.: From basic Network Principles to Neural Architecture, Proc. Natl. Acad. Sci. USA, Vol.83, 3 Parts: Emergence of spatial-opponent cells, p.7508–7512, Emergence of orientation-selective cells, p.8390–8394, Emergence of orientation columns, p.8779–8783

    Google Scholar 

  12. Linsker, R.: Self-Organization in a Perceptual Network, IEEE Computer, March 1988, p. 105–117

    Google Scholar 

  13. May, D.: OCCAM, SIGPLAN Notices, Vol.18, April 1983, S.69–79

    Google Scholar 

  14. Mündemann, F.W.: Konzepte zur Verwaltung n-dimensionaler Felder als Operanden in Datenflußsynchronisierten Programmen, Ph.D. Thesis, Universität der Bundeswehr München, Fakultät für Informatik, Juni 1989 (in German)

    Google Scholar 

  15. Neural Works: An Introduction to Neural Computing, NeuralWorks User's Guide, NeuralWare Inc.; Sewickley, USA 1988

    Google Scholar 

  16. Osterloh, M.: Handlungsspielräume und Informationsverarbeitung, Huber 1983

    Google Scholar 

  17. Treleaven, P.C., Hopkins, R.P., Rautenbach, P.W.: Combining Data Flow and Control Flow Computing, The Computer Journal, Vol.25, Nr.2, Febr.1982, S.207–217

    Google Scholar 

  18. Widrow, B., Hinter, R.: Neural Nets for Adaptive Filtering and Adaptive Pattern Recognition, IEEE Computer, March 1988, p.25–39

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty for Computer Science, University of the Federal Armed Forces Munich, D-8014, Neubiberg

    Friedhelm W. Mündemann

  2. ICAS - Institute for Cybernetic Anthropology Starnberg, D-8130, Starnberg

    Friedhelm W. Mündemann

Authors
  1. Friedhelm W. Mündemann
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

J. D. Becker I. Eisele F. W. Mündemann

Rights and permissions

Reprints and permissions

Copyright information

© 1991 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Mündemann, F.W. (1991). Self-organization in computational systems: Advance of a new computational paradigm?. In: Becker, J.D., Eisele, I., Mündemann, F.W. (eds) Parallelism, Learning, Evolution. WOPPLOT 1989. Lecture Notes in Computer Science, vol 565. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55027-5_18

Download citation

  • DOI: https://doi.org/10.1007/3-540-55027-5_18

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-55027-3

  • Online ISBN: 978-3-540-46663-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation