Application of Neural Network Models for Mathematical Programming Problems: A State of Art Review

Artificial neural networks or neural networks (NN) are new computational models based on the working of biological neurons of human body. A NN model consists of an interactive system through which external or internal information flows. Nowadays, NN models are being used to deal with complex real pr...

Full description

Saved in:
Bibliographic Details
Published in:Archives of computational methods in engineering Vol. 27; no. 1; pp. 171 - 182
Main Author: Lachhwani, Kailash
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 01.01.2020
Springer Nature B.V
Subjects:
ISSN:1134-3060, 1886-1784
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial neural networks or neural networks (NN) are new computational models based on the working of biological neurons of human body. A NN model consists of an interactive system through which external or internal information flows. Nowadays, NN models are being used to deal with complex real problems. On the other hand, mathematical programming problems (MPPs) are a particular class of optimization problems with mathematical structure of objective function(s) and set of constraints. Use of NN models in solving MPPs is a complex area of research and researchers have tried to contribute to apply NN models on different mathematical programming problems. This paper describes classification of MPPs, different neural network models and the detailed literature review on application of NN models for solving different MPPs along with comprehensive analysis on references. Some new research issues and scopes are also discussed on the use of different NN models on MPPs. This paper aims to present the state of art literature review on the use of NNs for solving MPPs with constructive analysis to elaborate future research scope and new directions in this area for future researchers.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1134-3060
1886-1784
DOI:10.1007/s11831-018-09309-5