Skip to main content
Log in

Parallel computations and committee constructions

  • Topical Issue
  • Published:
Automation and Remote Control Aims and scope Submit manuscript

Abstract

The paper reviewed the results bearing out the deep-seated relation between the parallel computations and learning procedures for the laminated neural networks one of whose formalizations is represented by the theory of committee constructions. Additionally, consideration was given to two combinatorial problems concerned with learning pattern recognition in the class of affine committees—the problem of verifying existence of a three-element affine separating committee and that of element-minimal affine separating committee. The first problem was shown to be N P-complete, whereas the second problem is N P-hard and does not belong to the Apx class.

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

  1. Mazurov, Vl.D., On the Committee of a System of Convex Inequalities, in Proc. Int. Math. Congr., Moscow: Mosk. Gos. Univ., 1966, no. 14, p. 41.

    Google Scholar 

  2. Mazurov, Vl.D., Metod komitetov v zadachakh optimizatsii i klassifikatsii (Method of Committees in the Problems of Optimization and Classification), Moscow: Nauka, 1990.

    MATH  Google Scholar 

  3. Mazurov, Vl.D., Consistent Completion of Systems of Algorithms to Committee Technologies, Pattern Recognit. Image Anal., 1998, vol. 8, no. 4, pp. 501–506.

    MathSciNet  Google Scholar 

  4. Ablow, C.M. and Kaylor, D.J., Inconsistent Homogeneous Linear Inequalities, Bull. Am. Math. Soc., 1965, vol. 71, no. 5, p. 724.

    Article  MathSciNet  Google Scholar 

  5. Judd, J.S., Neural Network Design and Complexity of Learning, New York: MIT Press, 1990.

    Google Scholar 

  6. Lin, J.H. and Vitter, J.S., Complexity Results on Learning by Neural Nets, Machine Learning, 1991, vol. 6, pp. 211–230.

    Google Scholar 

  7. Blum, A.L. and Rivest, R.L., Training a 3-node Neural Network is NP-complete, Neural Networks, 1992, vol. 5, pp. 117–127.

    Article  Google Scholar 

  8. Mazurov, Vl.D., Committees of Inequality Systems and the Problem of Recognition, Kibernetika, 1971, no. 3, pp. 140–146.

    MathSciNet  Google Scholar 

  9. Khachai, M.Yu., On Computational Complexity of the Minimal Committee and Related Problems, Dokl. Ross. Akad. Nauk, 2006, vol. 406, no. 6, pp. 742–745.

    MathSciNet  Google Scholar 

  10. Hastad, J., Clique is Hard to Approximate within n 1−ε, Acta Mathematica, 1999, vol. 182, no. 13, pp. 105–142.

    Article  MATH  MathSciNet  Google Scholar 

  11. Dinur, I., Regev, O., and Smyth, C., The Hardness of 3-uniform Hypergraph Coloring, in Proc. 43rd Ann. IEEE Sympos. Foundat. Comput. Sci., 2002.

  12. Khachai, M.Yu., On the Computational and Approximational Complexity of the Problem of Minimal Separating Committee, Tavrich. Vest. Informatiki i Mat., 2006, no. 1, pp. 34–43.

Download references

Author information

Authors and Affiliations

Authors

Additional information

Original Russian Text © V.D. Mazurov, M.Yu. Khachai, 2007, published in Avtomatika i Telemekhanika, 2007, No. 5, pp. 182–192.

This work was supported by the Russian Foundation for Basic Research, projects nos. 07-07-00168 and 07-01-399, and the Council for Grants at the President of the Russian Federation, projects nos. NSH-5595.2006.1 and MD-6768.2006.1.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mazurov, V.D., Khachai, M.Y. Parallel computations and committee constructions. Autom Remote Control 68, 912–921 (2007). https://doi.org/10.1134/S0005117907050165

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0005117907050165

PACS numbers

Navigation