A Global Universality of Two-Layer Neural Networks with ReLU Activations
A Global Universality of Two-Layer Neural Networks with ReLU Activations
复制标题
具有 ReLU 激活的两层神经网络的全球通用性
DOI：
10.1155/2021/6637220
复制
发表时间：
2021
影响因子：
1.9
通讯作者：
Sawano Yoshihiro
中科院分区：
文献类型：
--
作者：
Hatano Naoya;Ikeda Masahiro;Ishikawa Isao;Sawano Yoshihiro
在本研究中，我们研究了神经网络的普遍性，它涉及函数空间中双层神经网络集合的密度。有许多工作可以处理紧集上的收敛。在本文中，我们通过适当引入范数来考虑全局收敛，以便我们的结果在任何紧集上都是一致的。
In the present study, we investigate a universality of neural networks, which concerns a density of the set of two‐layer neural networks in function spaces. There are many works that handle the convergence over compact sets. In the present paper, we consider a global convergence by introducing a norm suitably, so that our results will be uniform over any compact set.