TY - JOUR
T1 - Hierarchical fuzzy CMAC for nonlinear systems modeling
AU - Yu, Wen
AU - Rodríguez, Floriberto Ortiz
AU - Moreno-Armendariz, Marco A.
PY - 2008
Y1 - 2008
N2 - Since the fuzzy cerebellar model articulation controller (FCMAC) uses linguistic variables, it is highly intuitive and easily comprehended. Despite the FCMAC's good local generalization capability for approximating nonlinear functions and fast learning, a normal FCMAC requires huge memory, and its dimension increases exponentially with the number of inputs. In order to overcome the memory explosion problem, this paper proposes two types of hierarchical FCMAC (HFCMAC). Another contribution of the paper is that we give stable learning algorithms for these two HFCMACs. Backpropagation-like approach is applied to train each block with a time-varying learning rate, which is obtained by the input-to-state stability technique.
AB - Since the fuzzy cerebellar model articulation controller (FCMAC) uses linguistic variables, it is highly intuitive and easily comprehended. Despite the FCMAC's good local generalization capability for approximating nonlinear functions and fast learning, a normal FCMAC requires huge memory, and its dimension increases exponentially with the number of inputs. In order to overcome the memory explosion problem, this paper proposes two types of hierarchical FCMAC (HFCMAC). Another contribution of the paper is that we give stable learning algorithms for these two HFCMACs. Backpropagation-like approach is applied to train each block with a time-varying learning rate, which is obtained by the input-to-state stability technique.
KW - Fuzzy CMAC
KW - Hierarchical
KW - Recurrent
KW - Stable modeling
UR - http://www.scopus.com/inward/record.url?scp=54349112429&partnerID=8YFLogxK
U2 - 10.1109/TFUZZ.2008.926579
DO - 10.1109/TFUZZ.2008.926579
M3 - Artículo
SN - 1063-6706
VL - 16
SP - 1302
EP - 1314
JO - IEEE Transactions on Fuzzy Systems
JF - IEEE Transactions on Fuzzy Systems
IS - 5
ER -