Finite size scaling in neural networks

Abstract

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 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.

4 pages, RevTex, 5 figures, uses multicol.sty and psfig.sty

Cited by in corpus (2)

• Techniques of replica symmetry breaking and the storage problem of the McCulloch-Pitts neuron
• Comment on "Finite size scaling in Neural Networks"