|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'504'928
Articles rated: 2609
25 April 2024 |
|
| | | | |
|
Article overview
| |
|
|
Finite size scaling in neural networks | | Walter Nadler
; Wolfgang Fink
; | | Date: |
5 Nov 1996 | | Subject: | Disordered Systems and Neural Networks; Adaptation and Self-Organizing Systems | cond-mat.dis-nn adap-org nlin.AO | | Affiliation: | Institut fuer Theoretische Chemie, Universitaet Tuebingen) and Wolfgang Fink (Institut fuer Theoretische Physik, Universitaet Tuebingen | | 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 alpha_c from simulations of relatively small systems. We illustrate this approach by determining alpha_c, together with the finite size scaling exponent
u, for storing Gaussian patterns in committee and parity machines with binary couplings and up to K=5 hidden units. | | Source: | arXiv, cond-mat/9611027 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER