Finite Size Scaling in Neural Networks
Copyright policy )Finite Size Scaling in Neural Networks
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
- University of Tübingen Germany
- University of Tuebingen Germany
- Institute for Theoretical Physics Switzerland
FOS: Physical sciences, Disordered Systems and Neural Networks (cond-mat.dis-nn), Condensed Matter - Disordered Systems and Neural Networks, Adaptation and Self-Organizing Systems (nlin.AO), Nonlinear Sciences - Adaptation and Self-Organizing Systems
FOS: Physical sciences, Disordered Systems and Neural Networks (cond-mat.dis-nn), Condensed Matter - Disordered Systems and Neural Networks, Adaptation and Self-Organizing Systems (nlin.AO), Nonlinear Sciences - Adaptation and Self-Organizing Systems
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).4 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Top 10% impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!