Title :
A recurrent neuro-fuzzy network structure and learning procedure
Author :
Ballini, Rosangela ; Soares, Secundino ; Gomide, Fernando
Author_Institution :
DCA-FEEC, Univ. Estadual de Campinas, Sao Paulo, Brazil
fDate :
6/23/1905 12:00:00 AM
Abstract :
A novel recurrent neurofuzzy network is proposed in this paper. This model is constructed from fuzzy set models of neurons. The network has a multilayer, recurrent structure whose units are modeled through triangular norms and conorms, and weights are defined within the unit interval. The learning procedure developed is based on two main paradigms, the gradient search and associative reinforcement learning, that is, the output layer weights are adjusted via an error gradient method whereas a reward and punishment scheme updates the hidden layer weights. The recurrent neuro-fuzzy network is used to develop a model of a nonlinear process. Numerical results show that the neuro-fuzzy network proposed provides an accurate process model after a short period of learning time
Keywords :
function approximation; fuzzy neural nets; fuzzy set theory; gradient methods; learning (artificial intelligence); recurrent neural nets; search problems; associative reinforcement learning; function approximation; fuzzy neural networks; fuzzy set theory; gradient search; recurrent neural network; reward punishment scheme; system modeling; triangular norms; Function approximation; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Learning; Modeling; Neural networks; Neurons; Recurrent neural networks;
Conference_Titel :
Fuzzy Systems, 2001. The 10th IEEE International Conference on
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-7293-X
DOI :
10.1109/FUZZ.2001.1008922
