Neural network approach to solving fully fuzzy nonlinear systems

Sina Razvarz, Raheleh Jafari, Alexander Gegov

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review

Abstract

The value of fuzzy designs improves whenever a system cannot be validated in precise mathematical terminologies. In this book chapter, two types of neural networks are applied to obtain the approximate solutions of the fully fuzzy nonlinear system (FFNS). For obtaining the approximate solutions, a superior gradient descent algorithm is proposed in order to train the neural networks. Several examples are illustrated to disclose high precision as well as the effectiveness of the proposed methods. The MATLAB environment is utilized to generate the simulations.
Original languageEnglish
Title of host publicationFuzzy Modelling and Control
EditorsTerrell Harvey, Dallas Mullins
PublisherNova Science Publishers
Chapter3
Pages46-68
Number of pages23
ISBN (Electronic)9781536134155
ISBN (Print)9781536134148
Publication statusPublished - 1 May 2018

Publication series

NameMathematics Research Developments
PublisherNova Science Publishers

Keywords

  • fully fuzzy nonlinear system
  • neural network
  • approximate solution

Fingerprint

Dive into the research topics of 'Neural network approach to solving fully fuzzy nonlinear systems'. Together they form a unique fingerprint.

Cite this