TY  - JOUR
N1  - cited By 21
N2  - Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. The robustness of the learning algorithm is discussed in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. An intelligent adaptation rule is developed for the learning rate of RBFNN which gives faster convergence via an estimate of error energy while giving guarantee to the l 2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development. © 2014 Syed Saad Azhar Ali et al.
KW  - article; computer simulation; controlled study; feedback system; learning algorithm; measurement error; nerve cell; nonlinear system; pattern recognition; radial based function; steady state; theoretical model; time series analysis; uncertainty; adaptive learning rate; Article; feedback system; prediction; radial basis function neural network; simulation; algorithm; artificial neural network
KW  -  Algorithms; Feedback; Neural Networks (Computer)
TI  - An adaptive learning rate for RBFNN using time-domain feedback analysis
ID  - scholars5438
AV  - none
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84897543058&doi=10.1155%2f2014%2f850189&partnerID=40&md5=80887e8df04e77b3bfbc35f665dd9de8
A1  - Ali, S.S.A.
A1  - Moinuddin, M.
A1  - Raza, K.
A1  - Adil, S.H.
JF  - The Scientific World Journal
VL  - 2014
Y1  - 2014///
SN  - 1537744X
PB  - ScientificWorld Ltd.
ER  -