Skip to main content
SpringerLink
Log in

A lower bound for monotone perceptrons

  • Published:
Mathematical systems theory Aims and scope Submit manuscript

Abstract

It is proved that there is a monotone function in AC 04 which requires exponential-size monotone perceptrons of depth 3. This solves the monotone version of a problem which, in the general case, would imply an oracle separation of PPPH.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. E. Allender, A note on the power of threshold circuits,Proceedings of the 30th IEEE Symposium on Foundations of Computer Science, 1989, pp. 580–584.

  2. J. Aspnes, R. Beigel, M. Furst, and S. Rudich, The expressive power of voting polynomials,Proceedings of the 23rd Annual ACM Symposium on Theory of Computing, ACM Press, New York, 1991, pp. 402–409.

    Google Scholar 

  3. R. Beigel, Perceptions, PP, and the polynomial hierarchy,Proceedings of the Seventh Annual Conference on Structure in Complexity Theory, IEEE Computer Society Press, New York, 1992, pp. 14–19.

    Google Scholar 

  4. R. Beigel, N. Reingold, and D. Spielman, PP is closed under intersection,Proceedings of the 23rd Annual ACM Symposium on Theory of Computing, IEEE Computer Society Press, New York, 1991, pp. 1–9. Also inJ. Comput. System. Sci., to appear.

    Google Scholar 

  5. R. Beigel, N. Reingold, and D. Spielman, The perceptron strikes back,Proceedings of the Sixth Annual Conference on Structure in Complexity Theory, IEEE Computer Society Press, New York, 1991, pp. 286–291.

    Google Scholar 

  6. F. Green, An oracle separating ⊕P from PPPH,Inform. Process. Lett. 37 (1991), pp. 149–153.

    Google Scholar 

  7. A. Hajnal, W. Maass, P. Pudlàk, M. Szegedy, and G. Turàn, Threshold circuits of bounded depth,Proceedings of the 28th Annual IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, New York, 1987, pp. 99–110.

    Google Scholar 

  8. J. Håstad, Computational Limitations for Small-Depth Circuits, MIT Press, Cambridge, MA, 1987.

    Google Scholar 

  9. J. Håstad and M. Goldmann, On the power of small-depth threshold circuits,Computat. Complexity,1 (1991), 113–129.

    Google Scholar 

  10. M. L. Minsky and S. A. Papert,Perceptions (expanded edition), MIT Press, Cambridge, MA, 1988.

    Google Scholar 

  11. J. Tarui, Randomized polynomials, threshold circuits, and the polynomial hierarchy,Proceedings of the 8th Annual Symposium on Theoretical Aspects of Computer Science, Lecture Notes in Computer Science, Vol. 480, Springer-Verlag, Berlin, 1991, pp. 238–250.

    Google Scholar 

  12. S. Toda, On the computational power of PP and ⊕P,Proceedings of the 30th IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, New York, 1989, pp. 514–519.

    Google Scholar 

  13. A. C.-C. Yao, Circuits and local computation,Proceedings of the 21st ACM Symposium on Theory of Computing ACM Press New York, 1989, pp. 186–196.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics and Computer Science, Clark University, 01610, Worcester, MA, USA

    F. Green

Authors
  1. F. Green
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Green, F. A lower bound for monotone perceptrons. Math. Systems Theory 28, 283–298 (1995). https://doi.org/10.1007/BF01185398

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01185398

Keywords

Search

Navigation