Normalization effects on shallow neural networks and related asymptotic expansions

DOI10.3934/fods.2021013zbMath1493.68325arXiv2011.10487MaRDI QIDQ2072629

Konstantinos V. Spiliopoulos, Jiahui Yu

Publication date: 26 January 2022

Published in: Foundations of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.10487

zbMATH Keywords

neural networks; asymptotic expansions; machine learning; initialization; out-of-sample performance; normalization effect

Mathematics Subject Classification ID

60F05: Central limit and other weak theorems

68T05: Learning and adaptive systems in artificial intelligence

60G99: Stochastic processes

62M45: Neural nets and related approaches to inference from stochastic processes

Uses Software

• CIFAR
• DeepFace
• DGM