Neural networks for of continuous optimal approximation functions in R^d |
| |
Authors: | Ting-fan Xie Xin-long Zhou |
| |
Affiliation: | 1. Department of Mathematics, China Jiliang University, 310018, Hangzhou, China 2. Department of Mathematics, University of Duisburg-Essen, 47048, Duisburg, Germany
|
| |
Abstract: | Using some regular matrices we present a method to express any multivariate algebraic polynomial of total order n in a normal form. Consequently, we prove constructively that, to approximate continuous target functions defined on some compact set of ? d , neural networks are at least as good as algebraic polynomials. |
| |
Keywords: | approximation rate neural network ridge function sigmoidal function. |
本文献已被 维普 SpringerLink 等数据库收录! |
|