Abstract
Original language | English |
---|---|
Pages (from-to) | 5311-5332 |
Number of pages | 22 |
Journal | Circuits, Systems and Signal Processing |
Volume | 37 |
Issue number | 12 |
Early online date | 19 May 2018 |
DOIs | |
Publication status | Published - Dec 2018 |
Fingerprint
Cite this
}
A Fractional Gradient Descent-Based RBF Neural Network. / Khan, Shujaat; Naseem, Imran; Malik, Muhammad Ammar; Togneri, Roberto; Bennamoun, Mohammed.
In: Circuits, Systems and Signal Processing, Vol. 37, No. 12, 12.2018, p. 5311-5332.Research output: Contribution to journal › Article
TY - JOUR
T1 - A Fractional Gradient Descent-Based RBF Neural Network
AU - Khan, Shujaat
AU - Naseem, Imran
AU - Malik, Muhammad Ammar
AU - Togneri, Roberto
AU - Bennamoun, Mohammed
PY - 2018/12
Y1 - 2018/12
N2 - In this research, we propose a novel fractional gradient descent-based learning algorithm (FGD) for the radial basis function neural networks (RBF-NN). The proposed FGD is the convex combination of the conventional, and the modified Riemann–Liouville derivative-based fractional gradient descent methods. The proposed FGD method is analyzed for an optimal solution in a system identification problem, and a closed form Wiener solution of a least square problem is obtained. Using the FGD, the weight update rule for the proposed fractional RBF-NN (FRBF-NN) is derived. The proposed FRBF-NN method is shown to outperform the conventional RBF-NN on four major problems of estimation namely nonlinear system identification, pattern classification, time series prediction and function approximation.
AB - In this research, we propose a novel fractional gradient descent-based learning algorithm (FGD) for the radial basis function neural networks (RBF-NN). The proposed FGD is the convex combination of the conventional, and the modified Riemann–Liouville derivative-based fractional gradient descent methods. The proposed FGD method is analyzed for an optimal solution in a system identification problem, and a closed form Wiener solution of a least square problem is obtained. Using the FGD, the weight update rule for the proposed fractional RBF-NN (FRBF-NN) is derived. The proposed FRBF-NN method is shown to outperform the conventional RBF-NN on four major problems of estimation namely nonlinear system identification, pattern classification, time series prediction and function approximation.
U2 - 10.1007/s00034-018-0835-3
DO - 10.1007/s00034-018-0835-3
M3 - Article
VL - 37
SP - 5311
EP - 5332
JO - Circuits, Systems and Signal Processing
JF - Circuits, Systems and Signal Processing
SN - 0278-081X
IS - 12
ER -