Hybrid training of recurrent fuzzy neural network model

Mojtaba Ahmadieh Khanesar*, Mahdi Aliyari Shoorehdeli, Mohammad Teshnehlab

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this study, a hybrid learning algorithm for training the Recurrent Fuzzy Neural Network (RFNN) is introduced. This learning algorithm aims to solve main problems of the Gradient Descent (GD) based methods for the optimization of the RFNNs, which are instability, local minima and the problem of generalization of trained network to the test data. PSO as a global optimizer is used to optimize the parameters of the membership functions and the GD algorithm is used to optimize the consequent part's parameters of RFNN. As PSO is a derivative free optimization technique, a simpler method for the train of RFNN is achieved. Also the results are compared to GD algorithm.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007
Number of pages6
Publication date2007
Pages2598-2603
Article number4303966
ISBN (Print)1424408288, 9781424408283
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007 - Harbin, China
Duration: 5 Aug 20078 Aug 2007

Conference

Conference2007 IEEE International Conference on Mechatronics and Automation, ICMA 2007
CountryChina
CityHarbin
Period05/08/200708/08/2007
SponsorIEEE, Harbin Engineering University, Kagawa University, National Natural Science Foundation of China, Ministry of Education, China

Keywords

  • Gradient descent
  • Identification
  • Particle swarm optimization
  • Prediction
  • Recurrent fuzzy neural network

Fingerprint Dive into the research topics of 'Hybrid training of recurrent fuzzy neural network model'. Together they form a unique fingerprint.

Cite this