Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1996-11-05
Physics
Condensed Matter
Disordered Systems and Neural Networks
4 pages, RevTex, 5 figures, uses multicol.sty and psfig.sty
Scientific paper
10.1103/PhysRevLett.78.555
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 \alpha_c from simulations of relatively small systems. We illustrate this approach by determining \alpha_c, together with the finite size scaling exponent \nu, for storing Gaussian patterns in committee and parity machines with binary couplings and up to K=5 hidden units.
Fink Wolfgang
Nadler Walter
No associations
LandOfFree
Finite size scaling in neural networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Finite size scaling in neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Finite size scaling in neural networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-56020