摘要
In recent years, functional neural networks have been proposed and studied in order to approximate nonlinear continuous functionals defined on L-P([-1, 1](S)) for integers S = 1 and 1 = P < 8. However, their theoretical properties are largely unknown beyond universality of approximation or the existing analysis does not apply to the rectified linear unit (ReLU) activation function. To fill in this void, we investigate here the approximation power of functional deep neural networks associated with the ReLU activation function by constructing a continuous piecewise linear interpolation under a simple triangulation. In addition, we establish rates of approximation of the proposed functional deep ReLU networks under mild regularity conditions. Finally, our study may also shed some light on the understanding of functional data learning algorithms.
学科与关键词
- Approximation of smooth functionals using deep ReLU networksSong, Linhao*; Liu, Ying; Fan, Jun; Zhou, Ding-XuanNeural Networks, 2023, 166: 424-436.被引 1
- Approximation of Nonlinear Functionals Using Deep ReLU Networks (vol 29, 50, 2023)Song, Linhao; Fan, Jun*; Chen, Di-Rong; Zhou, Ding-XuanJOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2023, 29(5): 57.
- SignReLU neural network and its approximation abilityLi, Jianfei; Feng, Han*; Zhou, Ding-XuanJournal of Computational and Applied Mathematics, 2024, 440: 115551.
