TY - JOUR
T1 - Nonlinear systems identification via two types of recurrent fuzzy CMAC
AU - Rodriguez, Floriberto Ortiz
AU - Yu, Wen
AU - Moreno-Armendariz, Marco A.
N1 - Funding Information:
Acknowledgements Dr. M.A. Moreno-Armendariz would like to thanks to CIC-IPN and SIP-IPN under research grant 20070612.
PY - 2008/8
Y1 - 2008/8
N2 - Normal fuzzy CMAC neural network performs well for nonlinear systems identification because of its fast learning speed and local generalization capability for approximating nonlinear functions. However, it requires huge memory and the dimension increases exponentially with the number of inputs. It is difficult to model dynamic systems with static fuzzy CMACs. In this paper, we use two types of recurrent techniques for fuzzy CMAC to overcome the above problems. The new CMAC neural networks are named recurrent fuzzy CMAC (RFCMAC) which add feedback connections in the inner layers (local feedback) or the output layer (global feedback). The corresponding learning algorithms have time-varying learning rates, the stabilities of the neural identifications are proven.
AB - Normal fuzzy CMAC neural network performs well for nonlinear systems identification because of its fast learning speed and local generalization capability for approximating nonlinear functions. However, it requires huge memory and the dimension increases exponentially with the number of inputs. It is difficult to model dynamic systems with static fuzzy CMACs. In this paper, we use two types of recurrent techniques for fuzzy CMAC to overcome the above problems. The new CMAC neural networks are named recurrent fuzzy CMAC (RFCMAC) which add feedback connections in the inner layers (local feedback) or the output layer (global feedback). The corresponding learning algorithms have time-varying learning rates, the stabilities of the neural identifications are proven.
KW - Fuzzy CMAC
KW - Modeling
KW - Recurrent neural networks
UR - http://www.scopus.com/inward/record.url?scp=47849115114&partnerID=8YFLogxK
U2 - 10.1007/s11063-008-9081-1
DO - 10.1007/s11063-008-9081-1
M3 - Artículo
SN - 1370-4621
VL - 28
SP - 49
EP - 62
JO - Neural Processing Letters
JF - Neural Processing Letters
IS - 1
ER -