Neural Network Approach to Solving Fully Fuzzy Nonlinear Systems

Razvarz, Sina ; Jafari, Raheleh ; Gegov, Alexander ; Yu, Wen; Paul, Satyam

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.

Citation

Razvarz, S., Jafari, R., Gegov, A., Yu, W., & Paul, S. (2018). Neural Network Approach to Solving Fully Fuzzy Nonlinear Systems. In D. Mullins, & T. Harvey (Eds.), Fuzzy Modeling and Control: Methods, Applications and Research. Novel Publications

• Acceptance Date: Mar 1, 2018
• Publication Date: May 1, 2018
• Deposit Date: Mar 10, 2020
• Publisher: Novel Publications
• Book Title: Fuzzy Modeling and Control: Methods, Applications and Research
• ISBN: 978-1-53613-414-8
• Public URL: https://uwe-repository.worktribe.com/output/5633491
• Publisher URL: https://novapublishers.com/shop/fuzzy-modeling-and-control-methods-applications-and-research/