Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures

The radial basis function architecture and the multilayer perceptron architecture are very different approaches to neural networks in theory and practice. Considering their classification efficiency, both have different strengths; thus, the integration of these tools is an interesting but understudi...

Full description

Saved in:
Bibliographic Details
Main Author: László Kovács
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322489801342976
author László Kovács
author_facet László Kovács
author_sort László Kovács
collection DOAJ
description The radial basis function architecture and the multilayer perceptron architecture are very different approaches to neural networks in theory and practice. Considering their classification efficiency, both have different strengths; thus, the integration of these tools is an interesting but understudied problem domain. This paper presents a novel initialization method based on a distance-weighted homogeneity measure to construct a radial basis function network with fast convergence. The proposed radial basis function network is utilized in the development of an integrated RBF-MLP architecture. The proposed neural network model was tested in various classification tasks and the test results show superiority of the proposed architecture. The RBF-MLP model achieved nearly 40 percent better accuracy in the tests than the baseline MLP or RBF neural network architectures.
format Article
id doaj-art-a77e6ac66af044d7a8b3e27f783fce4d
institution Kabale University
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-a77e6ac66af044d7a8b3e27f783fce4d2025-08-20T03:49:22ZengMDPI AGMathematics2227-73902025-04-01139147110.3390/math13091471Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network ArchitecturesLászló Kovács0Institute of Informatics, University of Miskolc, H-3515 Miskolc, HungaryThe radial basis function architecture and the multilayer perceptron architecture are very different approaches to neural networks in theory and practice. Considering their classification efficiency, both have different strengths; thus, the integration of these tools is an interesting but understudied problem domain. This paper presents a novel initialization method based on a distance-weighted homogeneity measure to construct a radial basis function network with fast convergence. The proposed radial basis function network is utilized in the development of an integrated RBF-MLP architecture. The proposed neural network model was tested in various classification tasks and the test results show superiority of the proposed architecture. The RBF-MLP model achieved nearly 40 percent better accuracy in the tests than the baseline MLP or RBF neural network architectures.https://www.mdpi.com/2227-7390/13/9/1471redial basis functionneural networksparameter initializationdensity-based entropy
spellingShingle László Kovács
Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
Mathematics
redial basis function
neural networks
parameter initialization
density-based entropy
title Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
title_full Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
title_fullStr Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
title_full_unstemmed Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
title_short Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures
title_sort classification improvement with integration of radial basis function and multilayer perceptron network architectures
topic redial basis function
neural networks
parameter initialization
density-based entropy
url https://www.mdpi.com/2227-7390/13/9/1471
work_keys_str_mv AT laszlokovacs classificationimprovementwithintegrationofradialbasisfunctionandmultilayerperceptronnetworkarchitectures