Skip to main content
Log in

Some global properties of neural networks

  • Published:
Kybernetik Aims and scope Submit manuscript

Abstract

Some properties of the global behaviour of a model of neural network are considered.

The geometric concept of “quadrant-degeneration” is studied and it is shown to be independent of the algebraic concept of rank-degeneration. The results obtained are employed to solve some global problems of synthesis (i.e., independent of the initial state of the network) without the use of the theory of linear inequalities.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Accardi, L.: Rank and reverberations in neural networks. Kybernetik 8, 163–164 (1971).

    Google Scholar 

  • Arimoto, T.: Periodical sequences realizable by an autonomous net of threshold elements, papers of the Committee on Automaton and Automatic Control, Inst. Elec. Commun, of Japan, March 1963.

  • Burattini, E., Liesis, V.: To appear.

  • Caianiello, E. R.: Outline of a theory of thought processes and thinking machines. J. theor. Biol. 2, 204–235 (1961).

    Google Scholar 

  • — Decision equations and reverberations. Kybernetik 3, 98–100 (1966a).

    Google Scholar 

  • - A study of neural networks and reverberations. Bionics Symposium, Dayton, Ohio (1966b).

  • — Luca, A.de, Ricciardi, L. M.: Reverberations and control of neural networks. Kybernetik 4, 10–18 (1967).

    Google Scholar 

  • Elgot: Switching circuit theory and logical design, p. 225–245. September 1961.

  • Gantmacher: Matrix Theory. Chelsea 1960.

  • Rockafellar: Convex analysis. Princeton 1969.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Accardi, L., Aiello, A. Some global properties of neural networks. Kybernetik 10, 115–119 (1972). https://doi.org/10.1007/BF00292238

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00292238

Keywords

Navigation