Skip to content

Finite size scaling in neural networks

Walter Nadler, Wolfgang Fink

cond-mat.dis-nnarXiv:cond-mat/9611027

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 αc from simulations of relatively small systems. We illustrate this approach by determining αc, 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.

Create a lesson