Approximation by neural networks and learning theory |
| |
Affiliation: | 1. Fachbereich Mathematik, University of Magdeburg, Gebaude 18, Universitaetsplatz 2, Magdeburg, Germany 39106;2. University of Jena, Mathematisches Institut, Earnst-Abbe-Platz 4, Jena, Germany 7740;3. Institut fur Angewandte Mathematik, Universitat Braunschweig, Pockelsstrasse 14, Technische, Braunschweig, Germany 31806 |
| |
Abstract: | We consider the problem of Learning Neural Networks from samples. The sample size which is sufficient for obtaining the almost-optimal stochastic approximation of function classes is obtained. In the terms of the accuracy confidence function, we show that the least-squares estimator is almost-optimal for the problem. These results can be used to solve Smale's network problem. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|