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 …
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 …
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 …
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 …
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) …
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 …
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 …
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 …
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 …