Towards a Mathematical Understanding of Neural Network-Based Machine Learning: What We Know and What We Don't
Year: 2020
Author: Weinan E, Chao Ma, Lei Wu, Stephan Wojtowytsch
CSIAM Transactions on Applied Mathematics, Vol. 1 (2020), Iss. 4 : pp. 561–615
Abstract
The purpose of this article is to review the achievements made in the last few years towards the understanding of the reasons behind the success and subtleties of neural network-based machine learning. In the tradition of good old applied mathematics, we will not only give attention to rigorous mathematical results, but also pay attention to the insight we have gained from careful numerical experiments as well as the analysis of simplified models. Along the way, we also list the open problems which we believe to be the most important topics for further study. This is not a complete overview over this quickly moving field, but we hope to provide a perspective which may be helpful especially to new researchers in the area.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/csiam-am.SO-2020-0002
CSIAM Transactions on Applied Mathematics, Vol. 1 (2020), Iss. 4 : pp. 561–615
Published online: 2020-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 55
Keywords: Neural networks machine learning supervised learning regression problems approximation optimization estimation a priori estimates Barron space multi-layer space flow-induced function space.