A fractional gradient descent-based rbf neural network

S Khan, I Naseem, MA Malik, R Togneri… - Circuits, Systems, and …, 2018 - Springer
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 …

A novel fractional gradient-based learning algorithm for recurrent neural networks

S Khan, J Ahmad, I Naseem, M Moinuddin - Circuits, Systems, and Signal …, 2018 - Springer
In this research, we propose a novel algorithm for learning of the recurrent neural networks
called as the fractional back-propagation through time (FBPTT). Considering the potential of …

Enhanced q-least Mean Square

A Sadiq, S Khan, I Naseem, R Togneri… - Circuits, Systems, and …, 2019 - Springer
In this work, a new class of stochastic gradient algorithm is developed based on q-calculus.
Unlike the existing q-LMS algorithm, the proposed approach fully utilizes the concept of q …

A robust variable step size fractional least mean square (rvss-flms) algorithm

S Khan, M Usman, I Naseem, R Togneri… - 2017 IEEE 13th …, 2017 - ieeexplore.ieee.org
In this paper, we propose an adaptive framework for the variable step size of the fractional
least mean square (FLMS) algorithm. The proposed algorithm named the robust variable …

Fclms: Fractional complex lms algorithm for complex system identification

J Ahmad, S Khan, M Usman, I Naseem… - 2017 IEEE 13th …, 2017 - ieeexplore.ieee.org
In this paper, a fractional order calculus based least mean square algorithm is proposed for
complex system identification. The proposed algorithm, named as, fractional complex least …

q-lmf: Quantum calculus-based least mean fourth algorithm

A Sadiq, M Usman, S Khan, I Naseem… - … Congress on Information …, 2020 - Springer
Herein, we propose a new class of stochastic gradient algorithm for channel identification.
The proposed q-least mean fourth (q-LMF) is an extension of the least mean fourth (LMF) …

Chaotic time series prediction using spatio-temporal rbf neural networks

A Sadiq, MS Ibrahim, M Usman… - 2018 3rd International …, 2018 - ieeexplore.ieee.org
Due to the dynamic nature, chaotic time series are difficult predict. In conventional signal
processing approaches signals are treated either in time or in space domain only. Spatio …

Variable fractional power‐least mean square based control algorithm with optimized PI gains for the operation of dynamic voltage restorer

TA Naidu, SR Arya, R Maurya… - IET Power …, 2021 - Wiley Online Library
Abstract The operation of Dynamic Voltage Restorer has been studied for the mitigation of
supply voltage disturbances like sag, swell, distortions, and unbalances. A Dynamic Voltage …

An Adaptive Learning Rate Deep Learning Optimizer Using Long and Short-Term Gradients Based on G–L Fractional-Order Derivative

S Chen, C Zhang, H Mu - Neural Processing Letters, 2024 - Springer
Deep learning model is a multi-layered network structure, and the network parameters that
evaluate the final performance of the model must be trained by a deep learning optimizer. In …

VP-FLMS: a novel variable power fractional LMS algorithm

S Khan, M Usman, I Naseem, R Togneri… - … on Ubiquitous and …, 2017 - ieeexplore.ieee.org
In this paper, we propose an adaptive framework for the variable power of the fractional least
mean square (FLMS) algorithm using the concept of instantaneous error energy. The …