Interpolation and rates of convergence for a class of neural networks |
| |
| Authors: | Feilong Cao Yongquan Zhang Ze-Rong He |
| |
| Institution: | 1. Department of Information and Mathematics Sciences, China Jiliang University, Hangzhou 310018, Zhejiang Province, PR China;2. Institute of Operational Research and Cybernetics, Hangzhou Dianzi University, Hangzhou 310018, Zhejiang Province, PR China |
| |
| Abstract: | This paper presents a type of feedforward neural networks (FNNs), which can be used to approximately interpolate, with arbitrary precision, any set of distinct data in multidimensional Euclidean spaces. They can also uniformly approximate any continuous functions of one variable or two variables. By using the modulus of continuity of function as metric, the rates of convergence of approximate interpolation networks are estimated, and two Jackson-type inequalities are established. |
| |
| Keywords: | Neural networks Interpolation Approximation Estimate of error |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
