A time-delay neural network model for unconstrained nonconvex optimization

Lizhi LIAO, Yu Hong Dai*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

In this paper, we first present some theoretical properties which include the convergence and bounds of both the trajectory and energy function for general neural network models for unconstrained nonconvex optimization problems. Based on this analysis, a novel time-delay neural network model is proposed for unconstrained nonconvex optimization. The simulation results of the new neural network on two examples indicate that the new neural network is quite efficient and outperforms the gradient neural network.

Original languageEnglish
Title of host publicationNumerical Analysis and Optimization - NAO-IV, 2017
EditorsLucio Grandinetti, Mehiddin Al-Baali, Anton Purnama
PublisherSpringer New York LLC
Pages155-171
Number of pages17
ISBN (Print)9783319900254
DOIs
Publication statusPublished - 2018
Event4th International Conference on Numerical Analysis and Optimization, NAO-IV 2017 - Muscat, Oman
Duration: 2 Jan 20175 Jan 2017

Publication series

NameSpringer Proceedings in Mathematics and Statistics
Volume235
ISSN (Print)2194-1009
ISSN (Electronic)2194-1017

Conference

Conference4th International Conference on Numerical Analysis and Optimization, NAO-IV 2017
Country/TerritoryOman
CityMuscat
Period2/01/175/01/17

Scopus Subject Areas

  • General Mathematics

User-Defined Keywords

  • Barzilai-Borwein method
  • Neural network
  • Time-delay
  • Unconstrained optimization

Fingerprint

Dive into the research topics of 'A time-delay neural network model for unconstrained nonconvex optimization'. Together they form a unique fingerprint.

Cite this