Skip to main content
Log in

To the mathematical theory of representation of information in neural nets

  • Brief Communications
  • Published:
Ukrainian Mathematical Journal Aims and scope

Abstract

We study irreducible nonorthogonal resolutions of the identity. The results obtained show that, in contrast to traditional requirements of “independent measurements” type, the noncommutative approach gives a more precise description of information systems.

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.

References

  1. A. S. Kholevo,Probabilistic and Statistical Aspects of Quantum Mechanics [in Russian], Nauka, Moscow (1980).

    Google Scholar 

  2. A. F. Zaritskii, “Probabilistic-operator measures in neural structures,” in:Numerical Methods of Analysis, Moscow University, Moscow (1995), pp. 105–115.

    Google Scholar 

  3. Yu. N. Bespalov, “Collections of orthoprojectors with relations,”Ukr. Mat. Zh.,44, No. 3, 309–317 (1992).

    Google Scholar 

  4. A. Yu. Piryatinskaya and Yu. S. Samoilenko, “Wild problems in the theory of representations of *-algebras generated by generatrices and relations,”Ukr. Mat. Zh.,47, No. 1, 70–78 (1995).

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Additional information

Translated from Ukrainskii Matematicheskii Zhurnal, Vol. 47, No. 12, pp. 1706–1707, December, 1995.

The author is grateful to Yu. N. Bespalov and Yu. S. Samoilenko for fruitful discussions on the theory of representations of*-algebras and useful comments.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zaritskii, A.F. To the mathematical theory of representation of information in neural nets. Ukr Math J 47, 1951–1952 (1995). https://doi.org/10.1007/BF01060969

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01060969

Keywords

Navigation