In this research, we focus on making a comparative study between different learning algorithms that have been proposed to train fuzzy neural networks, which has attracted a lot of attention for nonlinear system modeling. Thus, an analyzing of recent training algorithms and methods for FNNs is presented regarding their main structures, advantages, shortcomings, computational complexity, and training time for convergence. Moreover, an elaborated study of fixed structure or self-organized fuzzy neural networks is carried out as step toward using FNN in nonlinear system modeling.
Фахро К. (науч. рук. Пыркин А.А.) COMPARISON OF LEARNING ALGORITHMS FOR FUZZY NEURAL NETWORKS (FNN) USED FOR NONLINEAR SYSTEMS MODELING // Сборник тезисов докладов конгресса молодых ученых. Электронное издание. – СПб: Университет ИТМО, [2023]. URL: https://kmu.itmo.ru/digests/article/10952