Phys. Rev. Lett. 78, 555–558 (1997)

Finite Size Scaling in Neural Networks

Abstract

References

Citing Articles (4)

Download: PDF (108 kB) Buy this article Export: BibTeX or EndNote (RIS)

Walter Nadler
Institut für Theoretische Chemie, Universität Tübingen, Auf der Morgenstelle 8, D-72076 Tübingen, Germany

Wolfgang Fink
Institut für Theoretische Physik, Universität Tübingen, Auf der Morgenstelle 14, D-72076 Tübingen, Germany

Received 25 July 1996; published in the issue dated 20 January 1997

We demonstrate that the fraction of pattern sets that can be stored in single- and hidden-layer perceptrons exhibits finite size scaling. This feature allows one to estimate the critical storage capacity α_c from simulations of relatively small systems. We illustrate this approach by determining α_c, together with the finite size scaling exponent ν, for storing Gaussian patterns in committee and parity machines with binary couplings and up to K = 5 hidden units.

URL:

http://link.aps.org/doi/10.1103/PhysRevLett.78.555

DOI:

10.1103/PhysRevLett.78.555

PACS:

87.10.+e, 02.70.Lq, 05.50.+q, 64.60.Cn

Use of the American Physical Society websites and journals implies that the user has read and agrees to our Terms and Conditions and any applicable Subscription Agreement. Physical Review®, Physical Review Letters®, Reviews of Modern Physics®, and Physical Review Special Topics® are trademarks of the American Physical Society.

Citation Search:

Phys. Rev. Lett. 78, 555–558 (1997)

Finite Size Scaling in Neural Networks

See Also