Comment on "Finite size scaling in Neural Networks"
Disordered Systems and Neural Networks
2009-10-30 v2
Abstract
We use a binary search tree and the simplex algorithm to measure the fraction of patterns that can be stored by an Ising perceptron. The algorithm is much faster than exhaustive search and allows us to obtain accurate statistics up to a system size of N=42. The results show that the finite size scaling ansatz Nadler and Fink suggest in [1] cannot be applied to estimate accurately the storage capacity from small systems. [1] W.Nadler and W.Fink: Phys.Rev.Lett. 78, 555 (1997)
Keywords
Cite
@article{arxiv.cond-mat/9710178,
title = {Comment on "Finite size scaling in Neural Networks"},
author = {M. Schroeder and R. Urbanczik},
journal= {arXiv preprint arXiv:cond-mat/9710178},
year = {2009}
}
Comments
LaTeX with 1 postscript figure, using REVTeX