TY - JOUR
T1 - A Global Universality of Two-Layer Neural Networks with ReLU Activations
AU - Hatano, Naoya
AU - Ikeda, Masahiro
AU - Ishikawa, Isao
AU - Sawano, Yoshihiro
N1 - Publisher Copyright:
© 2021 Naoya Hatano et al.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85116320098&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116320098&partnerID=8YFLogxK
U2 - 10.1155/2021/6637220
DO - 10.1155/2021/6637220
M3 - Article
AN - SCOPUS:85116320098
SN - 2314-8896
VL - 2021
JO - Journal of Function Spaces
JF - Journal of Function Spaces
M1 - 6637220
ER -