Title
Mathematical Models of Overparameterized Neural Networks
Abstract
Deep learning has received considerable empirical success in recent years. However, while many ad hoc tricks have been discovered by practitioners, until recently, there has been a lack of theoretical understanding for tricks invented in the deep learning literature. Known by practitioners that overparameterized neural networks (NNs) are easy to learn, in the past few years, there have been import...
Year
DOI
Venue
2021
10.1109/JPROC.2020.3048020
Proceedings of the IEEE
Keywords
DocType
Volume
Artificial neural networks,Kernel,Mathematical model,Training,Radio frequency,Optimization,Linear programming
Journal
109
Issue
ISSN
Citations 
5
0018-9219
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Cong Fang1177.14
Hanze Dong202.03
Zhang, Tong37126611.43