An optimized radial basis function neural network with modulation-window activation function

It is a crucial basis to improve the performance of neural network by constructing an appropriate activation function. This paper proposes a novel modulation window radial basis function neural network (MW-RBFNN) with an adjustable activation function. In this MW-RBFNN, a raised cosine radial basis...

Full description

Saved in:
Bibliographic Details
Published in:Soft computing (Berlin, Germany) Germany), 2024-03, Vol.28 (5), p.4631-4648
Main Authors: Lin, Haijun, Dai, Houde, Mao, Yihan, Wang, Lucai
Format: Article
Language:English
Subjects:
Algorithms
Approximation
Artificial Intelligence
Computational Intelligence
Control
Engineering
Exponential functions
Mathematical Logic and Foundations
Mechatronics
Modulation
Neural Networks
Performance enhancement
Radial basis function
Robotics
Trigonometric functions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is a crucial basis to improve the performance of neural network by constructing an appropriate activation function. This paper proposes a novel modulation window radial basis function neural network (MW-RBFNN) with an adjustable activation function. In this MW-RBFNN, a raised cosine radial basis function (RC-RBF) is adaptively modulated by an exponential function, and served as a shape-tunable activation function of MW-RBFNN. Compared with the basic RC-RBF neural network, the approximating ability of MW-RBFNN is improved due to its shape-tunable activation function. Besides, the computation of MW-RBFNN is far less than that of Gaussian radial basis function neural network (GRBFNN) because the MW-RBFNN is compactly supported. The training algorithm of MW-RBFNN is provided and its approximating ability is proved. Moreover, the regulation mechanism of the modulation index for the NN’s performance is proved and the regulating algorithm of the modulation index in MW-RBFNN is given. The computational complexity of MW-RBFNN is also analyzed. Five typical application cases are presented to illustrate the effectiveness of this proposed MW-RBFNN.
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-023-09207-4