TY - JOUR
T1 - Boosting the performances of the recurrent neural network by the fuzzy min-max
AU - Zemouri, Ryad
AU - Filip, Florin Gheorghe
AU - Minca, Eugenia
AU - Racoceanu, Daniel
AU - Zerhouni, Noureddine
PY - 2009
Y1 - 2009
N2 - The k-means training algorithm used for the RBF (Radial Basis Function) neural network can have some weakness like empty clusters, the choice of the cluster number and the random choice of the centers of theses clusters. In this paper, we use the Fuzzy Min Max technique to boost the performances of the training algorithm. This technique is used to determine the number of the k centers and to initialize correctly these k centers. The k-means algorithm always converges to the same result for all the tests.
AB - The k-means training algorithm used for the RBF (Radial Basis Function) neural network can have some weakness like empty clusters, the choice of the cluster number and the random choice of the centers of theses clusters. In this paper, we use the Fuzzy Min Max technique to boost the performances of the training algorithm. This technique is used to determine the number of the k centers and to initialize correctly these k centers. The k-means algorithm always converges to the same result for all the tests.
KW - Fuzzy Min-Max
KW - K-means algorithm
KW - RBF network
KW - Recurrent network
KW - Time series prediction
UR - http://www.scopus.com/inward/record.url?scp=84878638008&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:84878638008
SN - 1453-8245
VL - 12
SP - 69
EP - 90
JO - Romanian Journal of Information Science and Technology
JF - Romanian Journal of Information Science and Technology
IS - 1
ER -