OpenAlex | Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class

Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class

Work

Year: 2023

Type: article

Abstract: In this paper, we construct neural networks with ReLU, sine, and as activation functions. For a general continuous defined on with continuity modulus , we construct -sine- networks that enjoy an appro... more

Source: SIAM Journal on Mathematical Analysis

Authors Yuling Jiao, Yanming Lai, Xiliang Lu, Fengru Wang, Jerry Zhijian Yang +1 more

Institution Wuhan University

Cites: 29

Cited by: 1

Related to: 10

FWCI: 0.285

Citation percentile (by year/subfield): 49.75

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders National Natural Science Foundation of China, National Natural Science Foundation of China, National Natural Science Foundation of China, National Natural Science Foundation of China

Grant IDS 12125103, 12071362, 11871385, 11871474