Multi-Kernel Fusion for RBF Neural Networks
This work addresses performance limitations in multi-kernel RBF neural networks for tasks like pattern classification, system identification, and function approximation, though it appears incremental as it builds on existing multi-kernel methods.
The paper tackles the problem of improving multi-kernel radial basis function neural networks by proposing a novel architecture where each base kernel has its own local weight, leading to faster convergence, better local minima, and resilience against poor minima, with empirical results showing superiority over state-of-the-art approaches.
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.