The Construction and Approximation of ReLU Neural Network Operators. (28th September 2022)

• Record Type: Journal Article
• Authors: Chen, Hengjie; Yu, Dansheng; Li, Zhong
• Other Names: Sawano Yoshihiro Academic Editor.
• Is Part Of: Journal of function spaces. Volume 2022(2022)
• Publication Date: 2022-09-28
• Subjects: Function spaces -- Periodicals; 515.7305
• DOI: 10.1155/2022/1713912
• Languages: English
• ISSNs: 2314-8896

Abstract

Abstract : In the present paper, we construct a new type of two-hidden-layer feedforward neural network operators with ReLU activation function. We estimate the rate of approximation by the new operators by using the modulus of continuity of the target function. Furthermore, we analyze features such as parameter sharing and local connectivity in this kind of network structure.