Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1703547 | Applied Mathematical Modelling | 2014 | 7 Pages |
Abstract
In this paper, we introduce a new type neural networks by superpositions of a sigmoidal function and study its approximation capability. We investigate the multivariate quantitative constructive approximation of real continuous multivariate functions on a cube by such type neural networks. This approximation is derived by establishing multivariate Jackson-type inequalities involving the multivariate modulus of smoothness of the target function. Our networks require no training in the traditional sense.
Related Topics
Physical Sciences and Engineering
Engineering
Computational Mechanics
Authors
Shaobo Lin, Yuanhua Rong, Zongben Xu,