A Proposal on Machine Learning via Dynamical Systems

W. Weinan

doi:10.1007/s40304-017-0103-z

A Proposal on Machine Learning via Dynamical Systems

W. Weinan

Mathematics

Research output: Contribution to journal › Article › peer-review

479 Scopus citations

Abstract

We discuss the idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning. We also discuss the connection with deep learning.

Original language	English (US)
Pages (from-to)	1-11
Number of pages	11
Journal	Communications in Mathematics and Statistics
Volume	5
Issue number	1
DOIs	https://doi.org/10.1007/s40304-017-0103-z
State	Published - Mar 1 2017

All Science Journal Classification (ASJC) codes

Statistics and Probability
Computational Mathematics
Applied Mathematics

Keywords

Deep learning
Dynamical systems
Machine learning

Access to Document

10.1007/s40304-017-0103-z

Cite this

@article{78ade847f940411bbdf46665ad13fdc1,

title = "A Proposal on Machine Learning via Dynamical Systems",

abstract = "We discuss the idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning. We also discuss the connection with deep learning.",

keywords = "Deep learning, Dynamical systems, Machine learning",

author = "W. Weinan",

note = "Publisher Copyright: {\textcopyright} 2017, School of Mathematical Sciences, University of Science and Technology of China and Springer-Verlag Berlin Heidelberg.",

year = "2017",

month = mar,

day = "1",

doi = "10.1007/s40304-017-0103-z",

language = "English (US)",

volume = "5",

pages = "1--11",

journal = "Communications in Mathematics and Statistics",

issn = "2194-6701",

publisher = "Springer Verlag",

number = "1",

}

TY - JOUR

T1 - A Proposal on Machine Learning via Dynamical Systems

AU - Weinan, W.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - We discuss the idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning. We also discuss the connection with deep learning.

AB - We discuss the idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning. We also discuss the connection with deep learning.

KW - Deep learning

KW - Dynamical systems

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85016198914&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016198914&partnerID=8YFLogxK

U2 - 10.1007/s40304-017-0103-z

DO - 10.1007/s40304-017-0103-z

M3 - Article

AN - SCOPUS:85016198914

SN - 2194-6701

VL - 5

SP - 1

EP - 11

JO - Communications in Mathematics and Statistics

JF - Communications in Mathematics and Statistics

IS - 1

ER -

A Proposal on Machine Learning via Dynamical Systems

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this