A modified Bayesian neural network integrating stochastic configuration network and ensemble learning strategy

In this paper, a stochastic configured Bayesian neural network (SCBNN) is proposed for solving regression and classification problems. Firstly, stochastic configuration network (SCN) is applied to extract feature. Then, the stochastic configured scheme is applied to Bayesian neural network (BNN) for...

Full description

Saved in:
Bibliographic Details
Published inProceedings (International Conference on Informative and Cybernetics for Computational Social Systems. Online) pp. 268 - 272
Main Authors Zheng, Hao, Wang, Degang, Zhou, Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.12.2021
Subjects
Bayes methods
Bayesian model average
Bayesian neural network
Computational modeling
Cybernetics
Feature extraction
Neural networks
Optimization
Stochastic configuration network
Stochastic processes
Online AccessGet full text
ISSN2639-4235
DOI10.1109/ICCSS53909.2021.9721995

Cover

More Information
Summary:In this paper, a stochastic configured Bayesian neural network (SCBNN) is proposed for solving regression and classification problems. Firstly, stochastic configuration network (SCN) is applied to extract feature. Then, the stochastic configured scheme is applied to Bayesian neural network (BNN) for obtaining the appropriate structure. The extracted features are combined with the original features to compute the output of the network. Further, an integration strategy of the Bayesian model average (BMA) is considered to improve the performance of the network. Some experimental results demonstrate the validity of the proposed method.
ISSN:2639-4235
DOI:10.1109/ICCSS53909.2021.9721995