Rates of Approximation by ReLU Shallow Neural Networks
–arXiv.org Artificial Intelligence
Neural networks activated by the rectified linear unit (ReLU) play a central role in the recent development of deep learning. The topic of approximating functions from H\"older spaces by these networks is crucial for understanding the efficiency of the induced learning algorithms. Although the topic has been well investigated in the setting of deep neural networks with many layers of hidden neurons, it is still open for shallow networks having only one hidden layer. In this paper, we provide rates of uniform approximation by these networks. We show that ReLU shallow neural networks with $m$ hidden neurons can uniformly approximate functions from the H\"older space $W_\infty^r([-1, 1]^d)$ with rates $O((\log m)^{\frac{1}{2} +d}m^{-\frac{r}{d}\frac{d+2}{d+4}})$ when $r
arXiv.org Artificial Intelligence
Jul-23-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America > United States
- New York > New York County
- New York City (0.04)
- California > Los Angeles County
- Claremont (0.04)
- New York > New York County
- Europe
- Russia (0.04)
- Germany (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Asia
- Oceania > Australia
- Genre:
- Research Report (0.64)
- Industry:
- Government (0.46)
- Technology: