Skip to main content

On lower bounds for the depth of threshold circuits with weights from {−1,0,+1}

  • 2 Inductive Inference for Artificial Intelligence
  • Chapter
  • First Online:
Algorithmic Learning for Knowledge-Based Systems

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 961))

Abstract

We consider boolean threshold circuits of polynomial size and constant depth. The threshold gates are of unbounded fan-in and with weights from {−1,0, +1}. We introduce the notation of sharp bounded density and prove that boolean functions f n (x) satisfying this property cannot be realized by threshold circuits of depth two with weights from {−1,0,+1}. Furthermore, some properties of threshold circuits are discussed resulting in lower bounds of depth four.

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

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. A. Albrecht. On the complexity of learning circuits. IIR, 5(12):29–35, 1989.

    Google Scholar 

  2. A. Albrecht. On bounded-depth threshold circuits for pattern functions. In Proc. of The International Conference on Artificial Neural Networks; ICANN'92, pages 135–138, Brighton, 1992.

    Google Scholar 

  3. E. Allender. A note on the power of threshold circuits. Technical Report TR-5, Univ. of Würzburg, Inst. of Informatics, July 1989.

    Google Scholar 

  4. E. Allender and V. Gore. On strong separations from AC 0. In Proc. 8th International Conference on Fundamentals of Computation Theory (FCT '91), Lecture Notes in Computer Science, volume 529, pages 1–15. Springer-Verlag, 1991.

    Google Scholar 

  5. E. Allender and V. Gore. A uniform circuit lower bound for the permanent. Technical report, Rutgers University, Dept. of Computer Science, 1992.

    Google Scholar 

  6. D.A. Barrington. Quasipolynomial size circuit classes. In Proc. 7th IEEE Structure in Complexity Theory Conference, pages 86–93, 1992.

    Google Scholar 

  7. D.A. Barrington and D. Thérien. Finite monoids and the fine structure of NC 0. J. Assoc. Comput. Mach., 35:941–952, 1988.

    Google Scholar 

  8. R. Beigel and J. Tarui. On ACC. In Proc. 32nd IEEE Symposium on Foundations of Computer Science, pages 783–792, 1991.

    Google Scholar 

  9. J. Bruck. Harmonic analysis of polynomial threshold functions. SIAM Journal on Discrete Mathematics, 3(2):168–177, 1990.

    Google Scholar 

  10. J. Bruck and R. Smolensky. Polynomial threshold functions, AC0 functions and spectral norms. In Proc. of the 31st IEEE Symp. on Foundations of Computer Science, pages 632–641, 1990.

    Google Scholar 

  11. M. Furst, J.B. Saxe, and M. Sipser. Parity, circuits, and the polynomial-time hierarchy. In Proc. 22nd IEEE Symp. on Foundations of Computer Science, pages 260–270, 1981.

    Google Scholar 

  12. M. Goldmann, J. Håstad, and A. Razborov. Majority gates vs. general weighted threshold gates. In Proc. 7th IEEE Structure in Complexity Theory Conf., 1992.

    Google Scholar 

  13. A. Hajnal, W. Maass, P. Pudlak, M. Szegedy, and G. Turan. Threshold functions of bounded depth. In Proc. 28 IEEE Symp. on Foundations of Computer Science, pages 99–110, 1987.

    Google Scholar 

  14. J. Håstad. Almost optimal lower bounds for small depth circuits. In Proc. of the 18th ACM Symp. on Theory of Computing, pages 6–20, 1986.

    Google Scholar 

  15. J. Håstad and M. Goldmann. On the power of small-depth threshold circuits. In Proc. of the 31st IEEE Symp. on Foundations of Computer Science, pages 610–618, 1990.

    Google Scholar 

  16. W. Maass, G. Schnitger, and E. Sontag. On the computational power of sigmoid versus boolean threshold circuits. In Proc. of the 32nd IEEE Symp. on Foundations of Computer Science, pages 767–776, 1991.

    Google Scholar 

  17. A.A. Razborov. Lower bounds on the size of bounded depth networks over a complete basis with logical addition; in Russian. Mathem. Zametki, 41:598–607, 1987.

    Google Scholar 

  18. K.-Y. Siu and J. Bruck. On the power of threshold circuits with small weights. SIAM Journal on Discrete Mathematics, 4(3):423–435, 1991.

    Google Scholar 

  19. R. Smolensky. Algebraic methods in the theory of lower bounds for boolean circuit complexity. In Proc. of the 19th ACM Symp. on Theory of Computing, pages 77–82, 1987.

    Google Scholar 

  20. Ph. Treleaven. Neurocomputers. Technical Report CS-RN-89-8, University College London, 1989.

    Google Scholar 

  21. K. Verbeurgt. Learning DNF under the uniform distribution in quasi-polynomial time. In Proc. of the 3 rd Annual Workshop on Computational Learning Theory, pages 314–326, 1990.

    Google Scholar 

  22. A.C. Yao. Circuits and local computation. In Proc. of the 21st ACM Symp. on Theory of Computing, pages 186–196, 1989.

    Google Scholar 

  23. A.C. Yao. On ACC and threshold circuits. In Proc. 31st IEEE Symposium on Foundations of Computer Science, pages 619–627, 1990.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Klaus P. Jantke Steffen Lange

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Albrecht, A. (1995). On lower bounds for the depth of threshold circuits with weights from {−1,0,+1}. In: Jantke, K.P., Lange, S. (eds) Algorithmic Learning for Knowledge-Based Systems. Lecture Notes in Computer Science, vol 961. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60217-8_19

Download citation

  • DOI: https://doi.org/10.1007/3-540-60217-8_19

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60217-0

  • Online ISBN: 978-3-540-44737-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics