arrow
Volume 28, Issue 5
Machine Learning and Computational Mathematics

Weinan E

Commun. Comput. Phys., 28 (2020), pp. 1639-1670.

Published online: 2020-11

Export citation
  • Abstract

Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, not just in traditional areas of artificial intelligence, but also in scientific computing and computational science. At the same time, machine learning has also acquired the reputation of being a set of "black box" type of tricks, without fundamental principles. This has been a real obstacle for making further progress in machine learning.
In this article, we try to address the following two very important questions: (1) How machine learning has already impacted and will further impact computational mathematics, scientific computing and computational science? (2) How computational mathematics, particularly numerical analysis, can impact machine learning? We describe some of the most important progress that has been made on these issues. Our hope is to put things into a perspective that will help to integrate machine learning with computational mathematics.

  • AMS Subject Headings

65Z99, 62G08, 62H99

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{CiCP-28-1639, author = {E , Weinan}, title = {Machine Learning and Computational Mathematics}, journal = {Communications in Computational Physics}, year = {2020}, volume = {28}, number = {5}, pages = {1639--1670}, abstract = {

Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, not just in traditional areas of artificial intelligence, but also in scientific computing and computational science. At the same time, machine learning has also acquired the reputation of being a set of "black box" type of tricks, without fundamental principles. This has been a real obstacle for making further progress in machine learning.
In this article, we try to address the following two very important questions: (1) How machine learning has already impacted and will further impact computational mathematics, scientific computing and computational science? (2) How computational mathematics, particularly numerical analysis, can impact machine learning? We describe some of the most important progress that has been made on these issues. Our hope is to put things into a perspective that will help to integrate machine learning with computational mathematics.

}, issn = {1991-7120}, doi = {https://doi.org/10.4208/cicp.OA-2020-0185}, url = {http://global-sci.org/intro/article_detail/cicp/18392.html} }
TY - JOUR T1 - Machine Learning and Computational Mathematics AU - E , Weinan JO - Communications in Computational Physics VL - 5 SP - 1639 EP - 1670 PY - 2020 DA - 2020/11 SN - 28 DO - http://doi.org/10.4208/cicp.OA-2020-0185 UR - https://global-sci.org/intro/article_detail/cicp/18392.html KW - Neural network-based machine learning, machine learning-based algorithm. AB -

Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, not just in traditional areas of artificial intelligence, but also in scientific computing and computational science. At the same time, machine learning has also acquired the reputation of being a set of "black box" type of tricks, without fundamental principles. This has been a real obstacle for making further progress in machine learning.
In this article, we try to address the following two very important questions: (1) How machine learning has already impacted and will further impact computational mathematics, scientific computing and computational science? (2) How computational mathematics, particularly numerical analysis, can impact machine learning? We describe some of the most important progress that has been made on these issues. Our hope is to put things into a perspective that will help to integrate machine learning with computational mathematics.

Weinan E. (2020). Machine Learning and Computational Mathematics. Communications in Computational Physics. 28 (5). 1639-1670. doi:10.4208/cicp.OA-2020-0185
Copy to clipboard
The citation has been copied to your clipboard