In this work, we explore the approximation capability of deep Rectified Quadratic Unit neural networks for H\"older-regular functions, with respect to the uniform norm. We find that theoretical approximation heavily depends on the selected activation function in the neural network.
翻译:在这项工作中,我们探索了H\“老常规功能”的深度整改二次脑细胞神经网络相对于统一规范的近似能力。 我们发现理论近似在很大程度上取决于神经网络中选择的激活功能。