Spatio-Temporal RBF Neural Networks

Khan, Shujaat; Jafarian, Ahmad; Sadiq, Alishba; Naseem, Imran; Moinuddin, Muhammad

doi:10.1109/iceest.2018.8643322

“…This hybrid approach for RBF outperformed conventional non-hybrid approaches. Another emerging variant of RBFNN called spatio-temporal RBFNN, uses the concept of time-space orthogonality to separately model the dynamics and nonlinear complexities [20,36]. Additionally, an adaptive Nelder Mead Simplex [12], based training method that simultaneously updates weights and kernel width is proposed in [15].…”

Section: Introductionmentioning

confidence: 99%

Multi-Kernel Fusion for RBF Neural Networks

Atif

¹

,

Khan

²

,

Naseem

³

et al. 2022

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

A simple yet effective architectural design of radial basis function neural networks (RBFNN) makes them amongst the most popular conventional neural networks. The current generation of radial basis function neural network is equipped with multiple kernels which provide significant performance benefits compared to the previous generation using only a single kernel. In existing multi-kernel RBF algorithms, multi-kernel is formed by the convex combination of the base/primary kernels. In this paper, we propose a novel multi-kernel RBFNN in which every base kernel has its own (local) weight. This novel flexibility in the network provides better performance such as faster convergence rate, better local minima and resilience against stucking in poor local minima. These performance gains are achieved at a competitive computational complexity compared to the contemporary multi-kernel RBF algorithms. The proposed algorithm is thoroughly analysed for performance gain using mathematical and graphical illustrations and also evaluated on three different types of problems namely: (i) pattern classification, (ii) system identification and (iii) function approximation. Empirical results clearly show the superiority of the proposed algorithm compared to the existing state-of-the-art multi-kernel approaches.

show abstract

“…This hybrid approach for RBF outperformed conventional nonhybrid approaches. Another emerging variant of RBFNN called spatio-temporal RBFNN, uses the concept of time-space orthogonality to separately model the dynamics and nonlinear complexities [20,36]. Additionally, an adaptive Nelder Mead Simplex [12], based training method that simultaneously updates weights and kernel width is proposed in [15].…”

Section: Introductionmentioning

confidence: 99%

Multi-Kernel Fusion for RBF Neural Networks

Atif¹,

Khan²,

Naseem³

et al. 2020

Preprint

Self Cite

0

View full text Add to dashboard Cite

A simple yet effective architectural design of radial basis function neural networks (RBFNN) makes them amongst the most popular conventional neural networks. The current generation of radial basis function neural network is equipped with multiple kernels which provide significant performance benefits compared to the previous generation using only a single kernel. In existing multikernel RBF algorithms, multi-kernel is formed by the convex combination of the base/primary kernels. In this paper, we propose a novel multi-kernel RBFNN in which every base kernel has its own (local) weight. This novel flexibility in the network provides better performance such as faster convergence rate, better local minima and resilience against stucking in poor local minima. These performance gains are achieved at a competitive computational complexity compared to the Both authors contributed equally.

show abstract

“…The concept of fractional calculus has been widely incorporated in various research areas [2], [3], [4], [5]. In [6], fractional order calculus was utilized a to propose a least mean square (LMS) algorithm.…”

Section: Introductionmentioning

confidence: 99%

Quantum Calculus-based Volterra LMS for Nonlinear Channel Estimation

Usman

¹

,

Ibrahim

²

,

Ahmed³

et al. 2019

2019 Second International Conference on Latest Trends in Electrical Engineering and Computing Technologies (INTELLECT)

Self Cite

View full text Add to dashboard Cite

A novel adaptive filtering method called q-Volterra least mean square (q-VLMS) is presented in this paper. The q-VLMS is a nonlinear extension of conventional LMS and it is based on Jackson's derivative also known as q-calculus. In Volterra LMS, due to large variance of input signal the convergence speed is very low. With proper manipulation we successfully improved the convergence performance of the Volterra LMS. The proposed algorithm is analyzed for the step-size bounds and results of analysis are verified through computer simulations for nonlinear channel estimation problem.

show abstract

Spatio-Temporal RBF Neural Networks

Cited by 4 publications

References 18 publications

Multi-Kernel Fusion for RBF Neural Networks

Multi-Kernel Fusion for RBF Neural Networks

Multi-Kernel Fusion for RBF Neural Networks

Quantum Calculus-based Volterra LMS for Nonlinear Channel Estimation

Contact Info

Product

Resources

About