Levenberg-Marcquardt Training Approach for Fuzzy-Neural Network

Yancho Todorov, Margarita Terziyska, Michail Petrov

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

This paper describes the development of a Levenberg-Marcquardt learning approach for the consequent part of the fuzzy rules in recurrent Takagi-Sugeno type inference. The recurrent relation in the proposed fuzzy-neural network represents a global feedback from the fuzzy-neural network output to its relevant inputs, being fuzzified in the next training sample. To prove the efficiency of the proposed fuzzy-neural structure, simulation experiments for prediction of Mackey-Glass chaotic time series are performed. A comparison with classical Gradient descent method is also studied.
Original languageEnglish
Title of host publicationInternational Conference "Automatics and Informatics" 2013, 03-07.10.2013, Sofia, Bulgaria
ISBN (Electronic)1313-1869
Publication statusPublished - 2013
MoE publication typeA4 Article in a conference publication
EventBulgarian Union of Automatics and Informatics - Sofia, Bulgaria
Duration: 3 Oct 20137 Oct 2013

Conference

ConferenceBulgarian Union of Automatics and Informatics
CountryBulgaria
CitySofia
Period03/10/201307/10/2013

Keywords

  • artificial intelligence
  • fuzzy systems
  • neural networks
  • process control
  • modeling
  • optimization

Fingerprint Dive into the research topics of 'Levenberg-Marcquardt Training Approach for Fuzzy-Neural Network'. Together they form a unique fingerprint.

Cite this