Nonlinear modeling with confidence estimation using Bayesian neural networks
There is a growing interest in the use of neural networks in civil engineering to model complicated nonlinearity problems. A recent enhancement to the conventional back-propagation neural network algorithm is the adoption of a Bayesian inference procedure that provides good generalization and a sta...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Electronic Journals for Science and Engineering - International
2004-01-01
|
Series: | Electronic Journal of Structural Engineering |
Subjects: | |
Online Access: | http://10.0.0.97/EJSE/article/view/45 |
_version_ | 1797733528558895104 |
---|---|
author | A.T.C. Goh C.G. Chua |
author_facet | A.T.C. Goh C.G. Chua |
author_sort | A.T.C. Goh |
collection | DOAJ |
description |
There is a growing interest in the use of neural networks in civil engineering to model complicated nonlinearity problems. A recent enhancement to the conventional back-propagation neural network algorithm is the adoption of a Bayesian inference procedure that provides good generalization and a statistical approach to deal with data uncertainty. A review of the Bayesian approach for neural network learning is presented. One distinct advantage of this method over the conventional back-propagation method is that the algorithm is able to provide assessments of the confidence associated with the network’s predictions. Two examples are presented to demonstrate the capabilities of this algorithm. A third example considers the practical application of the Bayesian neural network approach for analyzing the ultimate shear strength of deep beams.
|
first_indexed | 2024-03-12T12:29:24Z |
format | Article |
id | doaj.art-2902a762d8b142df84fca44335c831b7 |
institution | Directory Open Access Journal |
issn | 1443-9255 |
language | English |
last_indexed | 2024-03-12T12:29:24Z |
publishDate | 2004-01-01 |
publisher | Electronic Journals for Science and Engineering - International |
record_format | Article |
series | Electronic Journal of Structural Engineering |
spelling | doaj.art-2902a762d8b142df84fca44335c831b72023-08-29T11:47:50ZengElectronic Journals for Science and Engineering - InternationalElectronic Journal of Structural Engineering1443-92552004-01-014Nonlinear modeling with confidence estimation using Bayesian neural networksA.T.C. Goh0C.G. Chua1Nanyang Technological University Nanyang Technological University There is a growing interest in the use of neural networks in civil engineering to model complicated nonlinearity problems. A recent enhancement to the conventional back-propagation neural network algorithm is the adoption of a Bayesian inference procedure that provides good generalization and a statistical approach to deal with data uncertainty. A review of the Bayesian approach for neural network learning is presented. One distinct advantage of this method over the conventional back-propagation method is that the algorithm is able to provide assessments of the confidence associated with the network’s predictions. Two examples are presented to demonstrate the capabilities of this algorithm. A third example considers the practical application of the Bayesian neural network approach for analyzing the ultimate shear strength of deep beams. http://10.0.0.97/EJSE/article/view/45Back-propagation neural networkBayesian neural networkDeep beamsNeural networkNon-linear modelingUncertainty |
spellingShingle | A.T.C. Goh C.G. Chua Nonlinear modeling with confidence estimation using Bayesian neural networks Electronic Journal of Structural Engineering Back-propagation neural network Bayesian neural network Deep beams Neural network Non-linear modeling Uncertainty |
title | Nonlinear modeling with confidence estimation using Bayesian neural networks |
title_full | Nonlinear modeling with confidence estimation using Bayesian neural networks |
title_fullStr | Nonlinear modeling with confidence estimation using Bayesian neural networks |
title_full_unstemmed | Nonlinear modeling with confidence estimation using Bayesian neural networks |
title_short | Nonlinear modeling with confidence estimation using Bayesian neural networks |
title_sort | nonlinear modeling with confidence estimation using bayesian neural networks |
topic | Back-propagation neural network Bayesian neural network Deep beams Neural network Non-linear modeling Uncertainty |
url | http://10.0.0.97/EJSE/article/view/45 |
work_keys_str_mv | AT atcgoh nonlinearmodelingwithconfidenceestimationusingbayesianneuralnetworks AT cgchua nonlinearmodelingwithconfidenceestimationusingbayesianneuralnetworks |