Hybrid Training Method for Type-2 Fuzzy Neural Networks Using Particle Swarm Optimization

2016 ◽  
pp. 133-160 ◽  
Author(s):  
Erdal Kayacan ◽  
Mojtaba Ahmadieh Khanesar
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Fuzzy Neural Networks ◽  
Training Method ◽  
Swarm Optimization ◽  
Fuzzy Neural

scholarly journals Design and Verification of an Interval Type-2 Fuzzy Neural Network Based on Improved Particle Swarm Optimization

2020 ◽  
Vol 10 (9) ◽  
pp. 3041
Author(s):  
Cheng-Jian Lin ◽  
Shiou-Yun Jeng ◽  
Hsueh-Yi Lin ◽  
Cheng-Yi Yu
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Fuzzy Neural Network ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Improved Particle Swarm Optimization ◽  
Fuzzy Neural ◽  
Interval Type ◽  
Wall Following

In this study, we proposed an interval type-2 fuzzy neural network (IT2FNN) based on an improved particle swarm optimization (PSO) method for prediction and control applications. The noise-suppressing ability of the proposed IT2FNN was superior to that of the traditional type-1 fuzzy neural network. We proposed dynamic group cooperative particle swarm optimization (DGCPSO) with superior local search ability to overcome the local optimum problem of traditional PSO. The proposed model and related algorithms were verified through the accuracy of prediction and wall-following control of a mobile robot. Supervised learning was used for prediction, and reinforcement learning was used to achieve wall-following control. The experimental results demonstrated that DGCPSO exhibited superior prediction and wall-following control.

Sign in / Sign up

Export Citation Format

Share Document