Uncertainty quantification in Neural Networks by Approximate Bayesian Computation: Application to fatigue in composite materials

Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with uncertainty from different sources. Consequently, understanding if the model is indeed making accurate predictions or simply guessing at random is...

Full description

Saved in:
Bibliographic Details
Published in:Engineering applications of artificial intelligence Vol. 107; p. 104511
Main Authors: Fernández, Juan, Chiachío, Manuel, Chiachío, Juan, Muñoz, Rafael, Herrera, Francisco
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.01.2022
Subjects:
ISSN:0952-1976, 1873-6769
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with uncertainty from different sources. Consequently, understanding if the model is indeed making accurate predictions or simply guessing at random is not trivial, and measuring the confidence bounds becomes very important. Bayesian machine learning seems to provide the solution, however, many of the state-of-the-art Bayesian algorithms use rigid parametric representations of the uncertainty where the learning process depends on the gradient of a predefined cost function. In this article, a new gradient-free training algorithm based on Approximate Bayesian Computation by Subset Simulation is proposed, where the likelihood function and the weights are defined by non-parametric formulations, resulting in a flexible and fairer representation of the uncertainty. The experiments, specially the engineering case study on composite materials subject to fatigue damage, show the ability of the proposed algorithm to consistently reach accurate predictions while avoiding gradient related instabilities, and most importantly, it provides a realistic and coherent quantification of the uncertainty represented by confidence bounds. All this may lead to a reduction of safety factors in engineering problems, and in general, allows us to make well-informed decisions in situations with a high degree of uncertainty and risk. A comparison with the state-of-the-art Bayesian Neural Networks is also carried out. •Neural networks trained with approximate Bayesian computation.•Accurate and flexible representation of the uncertainty in the observed data.•Stability of predictions thanks to the gradient-free nature of the algorithm.•Non-parametric weights and likelihood function provide adaptability to data.•Appropriate when decisions are dependent on the level of uncertainty.
AbstractList Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with uncertainty from different sources. Consequently, understanding if the model is indeed making accurate predictions or simply guessing at random is not trivial, and measuring the confidence bounds becomes very important. Bayesian machine learning seems to provide the solution, however, many of the state-of-the-art Bayesian algorithms use rigid parametric representations of the uncertainty where the learning process depends on the gradient of a predefined cost function. In this article, a new gradient-free training algorithm based on Approximate Bayesian Computation by Subset Simulation is proposed, where the likelihood function and the weights are defined by non-parametric formulations, resulting in a flexible and fairer representation of the uncertainty. The experiments, specially the engineering case study on composite materials subject to fatigue damage, show the ability of the proposed algorithm to consistently reach accurate predictions while avoiding gradient related instabilities, and most importantly, it provides a realistic and coherent quantification of the uncertainty represented by confidence bounds. All this may lead to a reduction of safety factors in engineering problems, and in general, allows us to make well-informed decisions in situations with a high degree of uncertainty and risk. A comparison with the state-of-the-art Bayesian Neural Networks is also carried out. •Neural networks trained with approximate Bayesian computation.•Accurate and flexible representation of the uncertainty in the observed data.•Stability of predictions thanks to the gradient-free nature of the algorithm.•Non-parametric weights and likelihood function provide adaptability to data.•Appropriate when decisions are dependent on the level of uncertainty.
ArticleNumber 104511
Author Muñoz, Rafael
Herrera, Francisco
Chiachío, Juan
Fernández, Juan
Chiachío, Manuel
Author_xml – sequence: 1
  givenname: Juan
  orcidid: 0000-0002-9262-670X
  surname: Fernández
  fullname: Fernández, Juan
  email: juanfdez@ugr.es
  organization: Department of Structural Mechanics and Hydraulic Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada (UGR), Granada 18001, Spain
– sequence: 2
  givenname: Manuel
  surname: Chiachío
  fullname: Chiachío, Manuel
  organization: Department of Structural Mechanics and Hydraulic Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada (UGR), Granada 18001, Spain
– sequence: 3
  givenname: Juan
  orcidid: 0000-0003-1243-8694
  surname: Chiachío
  fullname: Chiachío, Juan
  organization: Department of Structural Mechanics and Hydraulic Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada (UGR), Granada 18001, Spain
– sequence: 4
  givenname: Rafael
  surname: Muñoz
  fullname: Muñoz, Rafael
  organization: Department of Civil Engineering, University of Granada (UGR), Granada 18001, Spain
– sequence: 5
  givenname: Francisco
  surname: Herrera
  fullname: Herrera, Francisco
  organization: Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada (UGR), Granada 18071, Spain
BookMark eNqFkMtOwzAQRS1UJErhF1B-IMVuEidBLCgVL6mCDV1b7mRSuaR2sB2gOz4dh9INm66uNZpz5TmnZKCNRkIuGB0zyvjleox6JdtWqvGETlgYphljR2TIijyJec7LARnSMpvErMz5CTl1bk0pTYqUD8n3QgNaL5X22-i9k9qrWoH0yuhI6egZOyubEP7T2DcXLbfRtG2t-VIb6TG6lVt0SupoZjZt53-xq36j2Xd4E9Xhteqwr4OwZpwKZI9bJRt3Ro7rEHj-lyOyuL97nT3G85eHp9l0HkPCqY-hqFiZYZnSNFliClBmnKWyrIoEJrTIMloXOUNWS0AKNeTAIYxLLHiVY82SEbne9YI1zlmsBajdh72VqhGMit6mWIu9TdHbFDubAef_8NYGB3Z7GLzZgRiO-1BohQOFQXqlLIIXlVGHKn4ABWGZXQ
CitedBy_id crossref_primary_10_1016_j_compind_2023_104058
crossref_primary_10_1016_j_ymssp_2025_112394
crossref_primary_10_1016_j_engappai_2023_107158
crossref_primary_10_1080_15397734_2024_2377257
crossref_primary_10_3390_polym17040550
crossref_primary_10_1016_j_prostr_2025_08_025
crossref_primary_10_1016_j_ijfatigue_2023_107538
crossref_primary_10_1016_j_engappai_2022_105539
crossref_primary_10_1016_j_compstruct_2023_117504
crossref_primary_10_1016_j_engappai_2023_105834
crossref_primary_10_1016_j_hybadv_2023_100026
crossref_primary_10_1016_j_ijfatigue_2023_108029
crossref_primary_10_1016_j_tws_2025_113914
crossref_primary_10_1016_j_measurement_2024_116092
crossref_primary_10_1016_j_engfracmech_2024_110120
crossref_primary_10_1016_j_istruc_2024_106100
crossref_primary_10_1016_j_ress_2023_109822
crossref_primary_10_1016_j_ijfatigue_2023_107731
crossref_primary_10_1016_j_ymssp_2023_110582
crossref_primary_10_1109_TITS_2025_3532803
crossref_primary_10_1016_j_compositesa_2024_108379
crossref_primary_10_1190_geo2023_0214_1
crossref_primary_10_1016_j_ins_2023_119716
crossref_primary_10_3390_pr10091716
crossref_primary_10_1016_j_engappai_2023_106517
crossref_primary_10_3390_electronics13091723
crossref_primary_10_1111_exsy_13040
crossref_primary_10_1007_s10338_024_00521_4
crossref_primary_10_1016_j_ymssp_2023_110713
crossref_primary_10_1016_j_engappai_2024_107871
crossref_primary_10_1007_s13349_022_00638_5
crossref_primary_10_1016_j_engappai_2022_105790
crossref_primary_10_1016_j_probengmech_2023_103507
crossref_primary_10_1016_j_ress_2024_110513
crossref_primary_10_1007_s10845_024_02343_0
crossref_primary_10_1016_j_cma_2024_117603
Cites_doi 10.1016/j.chaos.2019.07.011
10.1007/BF02478259
10.1002/wics.1486
10.1007/s10994-021-05946-3
10.1190/geo2018-0838.1
10.1061/9780784482933.343
10.1073/pnas.0306899100
10.1111/bmsp.12159
10.1016/j.compstruc.2011.10.017
10.1111/j.1467-9868.2011.01010.x
10.1109/SSCI47803.2020.9308463
10.1016/j.engappai.2005.09.001
10.1119/1.1990764
10.1093/mnras/staa523
10.1016/S0266-8920(01)00019-4
10.1016/j.engappai.2020.103761
10.1016/j.ijfatigue.2014.08.003
10.1109/IJCNN.2018.8489113
10.1089/big.2016.0051
10.1137/130932831
10.1214/12-STS406
10.1038/nature14541
10.4208/cicp.OA-2020-0165
10.1007/s11222-017-9764-4
10.1016/j.strusafe.2006.07.008
10.1016/j.compscitech.2008.04.042
10.1016/j.compositesa.2009.08.020
10.1016/j.asoc.2020.106996
10.1016/j.probengmech.2010.08.007
10.1155/2018/7068349
10.1038/s41386-020-0776-y
10.1016/j.cma.2004.05.028
10.1038/323533a0
10.1002/stc.424
10.1016/S0893-6080(00)00098-8
10.1016/j.procs.2019.01.007
10.1007/s11222-012-9328-6
10.1093/biomet/asp052
10.1007/s11222-011-9271-y
10.1016/j.dss.2020.113246
10.1162/neco.1992.4.3.448
10.1007/s11222-009-9116-0
10.1007/s11222-011-9288-2
ContentType Journal Article
Copyright 2021 The Author(s)
Copyright_xml – notice: 2021 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.engappai.2021.104511
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISSN 1873-6769
ExternalDocumentID 10_1016_j_engappai_2021_104511
S0952197621003596
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29G
4.4
457
4G.
5GY
5VS
6I.
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAFTH
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UHS
WUQ
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABJNI
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c360t-c8d195e94043be4cc95614a9d83c208550f871e1face0cfc7c6c0859e86d7ef13
ISICitedReferencesCount 39
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000747080100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0952-1976
IngestDate Tue Nov 18 22:12:19 EST 2025
Sat Nov 29 07:08:12 EST 2025
Fri Feb 23 02:40:07 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Approximate Bayesian Computation
Uncertainty quantification
Subset Simulation
Gradient-free training
Bayesian Neural Network
Non-parametric formulation
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c360t-c8d195e94043be4cc95614a9d83c208550f871e1face0cfc7c6c0859e86d7ef13
ORCID 0000-0002-9262-670X
0000-0003-1243-8694
OpenAccessLink https://dx.doi.org/10.1016/j.engappai.2021.104511
ParticipantIDs crossref_citationtrail_10_1016_j_engappai_2021_104511
crossref_primary_10_1016_j_engappai_2021_104511
elsevier_sciencedirect_doi_10_1016_j_engappai_2021_104511
PublicationCentury 2000
PublicationDate January 2022
2022-01-00
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: January 2022
PublicationDecade 2020
PublicationTitle Engineering applications of artificial intelligence
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Das, Pollack, Wollner, Mukerji (b24) 2019; 84
Blum, François (b14) 2010; 20
Sturman, von Ziegler, Schläppi, Akyol, Privitera, Slominski, Grimm, Thieren, Zerbi, Grewe (b67) 2020; 45
Talreja (b68) 2008; 68
Chiachío, Chiachío, Saxena, Sankararaman, Rus, Goebel (b20) 2015; 70
Lu (b48) 2020; 28
Pascanu, Mikolov, Bengio (b57) 2013
Marin, Pudlo, Robert, Ryder (b51) 2012
Bayes (b9) 1763; 53
Shin, Lee, Kim, Park, Lee, Min (b65) 2020; 94
Grazian, Fan (b34) 2020; 12
Beaumont, Cornuet, Marin, Robert (b10) 2009; 96
Ching, Au, Beck (b21) 2005; 194
Lampinen, Vehtari (b43) 2001; 14
Saxena, A., Goebel, K., Larrosa, C., Chank, F.-K., 2008. CFRP Composites Data Set, NASA Ames Prognostics Data Repository. NASA Ames Research Center, Moffett Field, CA. URL
Au, Beck (b5) 2001; 16
Levy, D., Sohl-dickstein, J., Hoffman, M., 2018. Generalizing Hamiltonian Monte Carlo with neural networks. In: ICLR 2018 Conference.
Neal (b55) 1993
Rumelhart, Hinton, Williams (b61) 1986; 323
Fearnhead, Prangle (b28) 2012; 74
Au, Ching, Beck (b6) 2007; 29
Chiachio, Beck, Chiachio, Rus (b19) 2014
Neal (b56) 1996
Zuev, Beck, Au, Katafygiotis (b76) 2012; 92–93
Awad, Elseuofi (b7) 2011; 3
Sriramula, Chryssanthopoulos (b66) 2009; 40
Maas, A.L., Hannun, A.Y., Ng, A.Y., 2013. Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing.
Ghahramani (b29) 2015; 521
Kingma, D.P., Ba, J., 2015. Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
Baragatti, Grimaud, Pommeret (b8) 2013; 23
Depeweg, Hernandez-Lobato, Doshi-Velez, Udluft (b26) 2018
.
Mcculloch, Pitts (b53) 1943; 5
Sadgali, Sael, Benabbou (b62) 2019; 148
Carlos-Roca, L.R., Torres, I.H., Tena, C.F., 2018. Facial recognition application for border control. In: 2018 International Joint Conference on Neural Networks. IJCNN. pp. 1–7.
Del Moral, Doucet, Jasra (b25) 2012; 22
Theano Development Team (b69) 2007
Hadjidoukas (b35) 2021
Altan, Karasu, Bekiros (b2) 2019; 126
Hüllermeier, Waegeman (b38) 2021; 110
Goodfellow, Warde-Farley, Mirza, Courville, Bengio (b32) 2013
Arora, Singh (b4) 2012; 60
Hernandez-Lobato, Adams (b36) 2015; vol. 37
Laplace (b44) 1812
Blum, Nunes, Prangle, Sisson (b15) 2013; 28
Vong, Wong, Li (b72) 2006; 19
Abadi, Agarwal, Barham, Brevdo, Chen, Citro, Corrado, Davis, Dean, Devin, Ghemawat, Goodfellow, Harp, Irving, Isard, Jia, Jozefowicz, Kaiser, Kudlur, Levenberg, Mané, Monga, Moore, Murray, Olah, Schuster, Shlens, Steiner, Sutskever, Talwar, Tucker, Vanhoucke, Vasudevan, Viégas, Vinyals, Warden, Wattenberg, Wicke, Yu, Zheng (b1) 2015
Jia, S., Yue, Y., Yang, Z., Pei, X., Wang, Y., 2020. Travelling modes recognition via Bayes neural network with Bayes by backprop algorithm. In: CICTP 2020. pp. 3994–4004.
Beck (b11) 2010; 17
List, Lewis (b47) 2020; 493
Dutta, Schoengens, Pacchiardi, Ummadisingu, Widmer, Onnela, Mira (b27) 2017
Benker, Furtner, Semm, Zaeh (b12) 2020; In Press
Prangle, Everitt, Kypraios (b59) 2018; 28
Blundell, Cornebise, Kavukcuoglu, Wierstra (b16) 2015; vol. 37
Gilks, Richardson, Spiegelhalter (b30) 1996
Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga, Desmaison, Kopf, Yang, DeVito, Raison, Tejani, Chilamkurthy, Steiner, Fang, Bai, Chintala (b58) 2019
Varshney, Alemzadeh (b71) 2017; 5
Buntine, Weigend (b17) 1991; 5
Goodfellow, Bengio, Courville (b31) 2016
Jiang, Wu, Zheng, Wong (b41) 2017; 27
Marjoram, Molitor, Plagnol, Tavaré (b52) 2003; 100
Radev, Mertens, Voss, Köthe (b60) 2020; 73
Voulodimos, Doulamis, Doulamis, Protopapadakis, Andina (b73) 2018; 2018
Betancourt (b13) 2017
Neal (b54) 1992
Cox (b23) 1946; 14
Jeffreys (b39) 1961
Hoffman, Blei, Wang, Paisley (b37) 2013; 14
Santoso, Phoon, Quek (b63) 2011; 26
MacKay (b50) 1992; 4
Zhang, Mahadevan (b75) 2020; 131
Larrosa Wilson, C., Chang, F.-K., 2012. Real time in-situ damage classification, quantification and diagnosis for composite structures. In: 19th International Congress on Sound and Vibration 2012, Vol. 4. ICSV 2012. pp. 2696–2704.
Van Rossum, Drake Jr. (b70) 1995
Graves (b33) 2011
Altan, Karasu, Zio (b3) 2021; 100
Chollet (b22) 2015
Wang, H., Bai, X., Tan, J., 2020. Uncertainty quantification of bearing remaining useful life based on convolutional neural network. In: 2020 IEEE Symposium Series on Computational Intelligence. SSCI. pp. 2893–2900.
Gilks (10.1016/j.engappai.2021.104511_b30) 1996
Theano Development Team (10.1016/j.engappai.2021.104511_b69) 2007
Cox (10.1016/j.engappai.2021.104511_b23) 1946; 14
10.1016/j.engappai.2021.104511_b74
Awad (10.1016/j.engappai.2021.104511_b7) 2011; 3
Buntine (10.1016/j.engappai.2021.104511_b17) 1991; 5
Neal (10.1016/j.engappai.2021.104511_b54) 1992
Graves (10.1016/j.engappai.2021.104511_b33) 2011
Blum (10.1016/j.engappai.2021.104511_b14) 2010; 20
Betancourt (10.1016/j.engappai.2021.104511_b13) 2017
Chiachío (10.1016/j.engappai.2021.104511_b20) 2015; 70
Pascanu (10.1016/j.engappai.2021.104511_b57) 2013
Voulodimos (10.1016/j.engappai.2021.104511_b73) 2018; 2018
Laplace (10.1016/j.engappai.2021.104511_b44) 1812
List (10.1016/j.engappai.2021.104511_b47) 2020; 493
Marjoram (10.1016/j.engappai.2021.104511_b52) 2003; 100
Arora (10.1016/j.engappai.2021.104511_b4) 2012; 60
Del Moral (10.1016/j.engappai.2021.104511_b25) 2012; 22
Blundell (10.1016/j.engappai.2021.104511_b16) 2015; vol. 37
Vong (10.1016/j.engappai.2021.104511_b72) 2006; 19
Goodfellow (10.1016/j.engappai.2021.104511_b32) 2013
Grazian (10.1016/j.engappai.2021.104511_b34) 2020; 12
Ching (10.1016/j.engappai.2021.104511_b21) 2005; 194
Mcculloch (10.1016/j.engappai.2021.104511_b53) 1943; 5
10.1016/j.engappai.2021.104511_b64
Lampinen (10.1016/j.engappai.2021.104511_b43) 2001; 14
Zhang (10.1016/j.engappai.2021.104511_b75) 2020; 131
Neal (10.1016/j.engappai.2021.104511_b55) 1993
Bayes (10.1016/j.engappai.2021.104511_b9) 1763; 53
Beck (10.1016/j.engappai.2021.104511_b11) 2010; 17
Santoso (10.1016/j.engappai.2021.104511_b63) 2011; 26
Jeffreys (10.1016/j.engappai.2021.104511_b39) 1961
Benker (10.1016/j.engappai.2021.104511_b12) 2020; In Press
Au (10.1016/j.engappai.2021.104511_b5) 2001; 16
Hadjidoukas (10.1016/j.engappai.2021.104511_b35) 2021
Sturman (10.1016/j.engappai.2021.104511_b67) 2020; 45
Paszke (10.1016/j.engappai.2021.104511_b58) 2019
Sadgali (10.1016/j.engappai.2021.104511_b62) 2019; 148
Altan (10.1016/j.engappai.2021.104511_b3) 2021; 100
Ghahramani (10.1016/j.engappai.2021.104511_b29) 2015; 521
Prangle (10.1016/j.engappai.2021.104511_b59) 2018; 28
Blum (10.1016/j.engappai.2021.104511_b15) 2013; 28
Hüllermeier (10.1016/j.engappai.2021.104511_b38) 2021; 110
Shin (10.1016/j.engappai.2021.104511_b65) 2020; 94
Au (10.1016/j.engappai.2021.104511_b6) 2007; 29
Jiang (10.1016/j.engappai.2021.104511_b41) 2017; 27
Talreja (10.1016/j.engappai.2021.104511_b68) 2008; 68
Beaumont (10.1016/j.engappai.2021.104511_b10) 2009; 96
Lu (10.1016/j.engappai.2021.104511_b48) 2020; 28
10.1016/j.engappai.2021.104511_b18
Dutta (10.1016/j.engappai.2021.104511_b27) 2017
Chollet (10.1016/j.engappai.2021.104511_b22) 2015
Van Rossum (10.1016/j.engappai.2021.104511_b70) 1995
Altan (10.1016/j.engappai.2021.104511_b2) 2019; 126
Baragatti (10.1016/j.engappai.2021.104511_b8) 2013; 23
Varshney (10.1016/j.engappai.2021.104511_b71) 2017; 5
Marin (10.1016/j.engappai.2021.104511_b51) 2012
Sriramula (10.1016/j.engappai.2021.104511_b66) 2009; 40
Goodfellow (10.1016/j.engappai.2021.104511_b31) 2016
Zuev (10.1016/j.engappai.2021.104511_b76) 2012; 92–93
10.1016/j.engappai.2021.104511_b40
Rumelhart (10.1016/j.engappai.2021.104511_b61) 1986; 323
10.1016/j.engappai.2021.104511_b42
Radev (10.1016/j.engappai.2021.104511_b60) 2020; 73
Hernandez-Lobato (10.1016/j.engappai.2021.104511_b36) 2015; vol. 37
Fearnhead (10.1016/j.engappai.2021.104511_b28) 2012; 74
Abadi (10.1016/j.engappai.2021.104511_b1) 2015
MacKay (10.1016/j.engappai.2021.104511_b50) 1992; 4
Hoffman (10.1016/j.engappai.2021.104511_b37) 2013; 14
10.1016/j.engappai.2021.104511_b46
Das (10.1016/j.engappai.2021.104511_b24) 2019; 84
Depeweg (10.1016/j.engappai.2021.104511_b26) 2018
10.1016/j.engappai.2021.104511_b45
Neal (10.1016/j.engappai.2021.104511_b56) 1996
Chiachio (10.1016/j.engappai.2021.104511_b19) 2014
10.1016/j.engappai.2021.104511_b49
References_xml – reference: Saxena, A., Goebel, K., Larrosa, C., Chank, F.-K., 2008. CFRP Composites Data Set, NASA Ames Prognostics Data Repository. NASA Ames Research Center, Moffett Field, CA. URL
– year: 2015
  ident: b22
  article-title: Keras
– volume: 22
  start-page: 1009
  year: 2012
  end-page: 1020
  ident: b25
  article-title: An adaptive sequential Monte Carlo method for approximate Bayesian computation
  publication-title: Stat. Comput.
– volume: 2018
  year: 2018
  ident: b73
  article-title: Deep learning for computer vision: a brief review
  publication-title: Comput. Intell. Neurosci.
– volume: 20
  start-page: 63
  year: 2010
  end-page: 73
  ident: b14
  article-title: Non-linear regression models for approximate Bayesian computation
  publication-title: Stat. Comput.
– volume: 5
  start-page: 127
  year: 1943
  end-page: 147
  ident: b53
  article-title: A logical calculus of ideas immanent in nervous activity
  publication-title: Bull. Math. Biophys.
– volume: 12
  year: 2020
  ident: b34
  article-title: A review of approximate Bayesian computation methods via density estimation: Inference for simulator-models
  publication-title: WIREs Comput. Stat.
– year: 1961
  ident: b39
  article-title: Theory of Probability
– volume: 100
  start-page: 15324
  year: 2003
  end-page: 15328
  ident: b52
  article-title: Markov chain Monte Carlo without likelihoods
  publication-title: Proc. Natl. Acad. Sci.
– volume: 53
  start-page: 370
  year: 1763
  end-page: 418
  ident: b9
  article-title: An essay towards solving a problem in the doctrine of chances
  publication-title: Phil. Trans. R. Soc. London
– volume: 84
  start-page: R869
  year: 2019
  end-page: R880
  ident: b24
  article-title: Convolutional neural network for seismic impedance inversion
  publication-title: Geophysics
– volume: In Press
  year: 2020
  ident: b12
  article-title: Utilizing uncertainty information in remaining useful life estimation via Bayesian neural networks and Hamiltonian Monte Carlo
  publication-title: J. Manuf. Syst.
– start-page: 2348
  year: 2011
  end-page: 2356
  ident: b33
  article-title: Practical variational inference for neural networks
  publication-title: Proceedings of the 24th International Conference on Neural Information Processing Systems
– volume: 126
  start-page: 325
  year: 2019
  end-page: 336
  ident: b2
  article-title: Digital currency forecasting with chaotic meta-heuristic bio-inspired signal processing techniques
  publication-title: Chaos Solitons Fractals
– volume: 5
  start-page: 603
  year: 1991
  end-page: 643
  ident: b17
  article-title: BayesIan back-propagation
  publication-title: Complex Syst.
– start-page: 1167
  year: 2012
  end-page: -1180
  ident: b51
  article-title: Approximate Bayesian computational methods
  publication-title: Stat. Comput.
– volume: 26
  start-page: 331
  year: 2011
  end-page: 341
  ident: b63
  article-title: Modified Metropolis–Hastings algorithm with reduced chain correlation for efficient subset simulation
  publication-title: Probab. Eng. Mech.
– reference: Kingma, D.P., Ba, J., 2015. Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
– volume: 323
  start-page: 533
  year: 1986
  end-page: 536
  ident: b61
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
– volume: 14
  year: 2013
  ident: b37
  article-title: Stochastic variational inference
  publication-title: J. Mach. Learn. Res.
– reference: Carlos-Roca, L.R., Torres, I.H., Tena, C.F., 2018. Facial recognition application for border control. In: 2018 International Joint Conference on Neural Networks. IJCNN. pp. 1–7.
– volume: vol. 37
  start-page: 1861
  year: 2015
  end-page: 1869
  ident: b36
  article-title: Probabilistic backpropagation for scalable learning of Bayesian neural networks
  publication-title: Proceedings of the 32nd International Conference on Machine Learning
– volume: 19
  start-page: 277
  year: 2006
  end-page: 287
  ident: b72
  article-title: Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference
  publication-title: Eng. Appl. Artif. Intell.
– year: 2007
  ident: b69
  article-title: Theano: A python framework for fast computation of mathematical expressions
– volume: 4
  start-page: 448
  year: 1992
  end-page: 472
  ident: b50
  article-title: A practical Bayesian framework for backpropagation networks
  publication-title: Neural Comput.
– volume: 3
  start-page: 173
  year: 2011
  end-page: 184
  ident: b7
  article-title: Machine learning methods for spam e-mail classification
  publication-title: Int. J. Comput. Sci. Inf. Technol.
– volume: 28
  start-page: 819
  year: 2018
  end-page: 834
  ident: b59
  article-title: A rare event approach to high-dimensional approximate Bayesian computation
  publication-title: Stat. Comput.
– volume: 16
  start-page: 263
  year: 2001
  end-page: 277
  ident: b5
  article-title: Estimation of small failure probabilities in high dimensions by subset simulation
  publication-title: Probab. Eng. Mech.
– reference: Maas, A.L., Hannun, A.Y., Ng, A.Y., 2013. Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing.
– start-page: A1339
  year: 2014
  end-page: -A1358
  ident: b19
  article-title: Approximate Bayesian computation by subset simulation
  publication-title: SIAM J. Sci. Comput.
– volume: 27
  start-page: 1595
  year: 2017
  end-page: 1618
  ident: b41
  article-title: Learning summary statistic for approximate Bayesian computation via deep neural network
  publication-title: Statist. Sinica
– year: 2021
  ident: b35
– volume: 14
  start-page: 257
  year: 2001
  end-page: 274
  ident: b43
  article-title: BayesIan approach for neural networks—review and case studies
  publication-title: Neural Netw.
– volume: 29
  start-page: 183
  year: 2007
  end-page: 193
  ident: b6
  article-title: Application of subset simulation methods to reliability benchmark problems
  publication-title: Struct. Saf.
– volume: 17
  start-page: 825
  year: 2010
  end-page: 847
  ident: b11
  article-title: BayesIan system identification based on probability logic
  publication-title: Struct. Control Health Monit.
– reference: Larrosa Wilson, C., Chang, F.-K., 2012. Real time in-situ damage classification, quantification and diagnosis for composite structures. In: 19th International Congress on Sound and Vibration 2012, Vol. 4. ICSV 2012. pp. 2696–2704.
– year: 1993
  ident: b55
  article-title: Probabilistic Inference Using Markov Chain Monte Carlo Methods
– volume: 14
  start-page: 1
  year: 1946
  end-page: 13
  ident: b23
  article-title: Probability, frequency, and reasonable expectation
  publication-title: Amer. J. Phys.
– volume: 70
  start-page: 361
  year: 2015
  end-page: 373
  ident: b20
  article-title: BayesIan model selection and parameter estimation for fatigue damage progression models in composites
  publication-title: Int. J. Fatigue
– year: 1996
  ident: b30
  article-title: Markov Chain Monte Carlo in Practice
– start-page: 8024
  year: 2019
  end-page: 8035
  ident: b58
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Advances in Neural Information Processing Systems 32
– volume: 60
  start-page: 34
  year: 2012
  end-page: 44
  ident: b4
  article-title: Automatic speech recognition: a review
  publication-title: Int. J. Comput. Appl.
– year: 1996
  ident: b56
  article-title: Bayesian Learning for Neural Networks
– volume: 73
  start-page: 23
  year: 2020
  end-page: 43
  ident: b60
  article-title: Towards end-to-end likelihood-free inference with convolutional neural networks
  publication-title: Br. J. Math. Stat. Psychol.
– volume: 110
  start-page: 457
  year: 2021
  end-page: 506
  ident: b38
  article-title: Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods
  publication-title: Mach. Learn.
– volume: 96
  start-page: 983
  year: 2009
  end-page: 990
  ident: b10
  article-title: Adaptive approximate Bayesian computation
  publication-title: Biometrika
– volume: 92–93
  start-page: 283
  year: 2012
  end-page: 296
  ident: b76
  article-title: BayesIan post-processor and other enhancements of Subset Simulation for estimating failure probabilities in high dimensions
  publication-title: Comput. Struct.
– year: 2017
  ident: b13
  article-title: A conceptual introduction to Hamiltonian Monte Carlo
– volume: 131
  year: 2020
  ident: b75
  article-title: BayesIan neural networks for flight trajectory prediction and safety assessment
  publication-title: Decis. Support Syst.
– year: 1992
  ident: b54
  article-title: Bayesian Training of Backpropagation Networks by the Hybrid Monte Carlo Method
– volume: 521
  start-page: 452
  year: 2015
  end-page: 459
  ident: b29
  article-title: Probabilistic machine learning and artificial intelligence
  publication-title: Nature
– volume: 68
  start-page: 2585
  year: 2008
  end-page: 2591
  ident: b68
  article-title: Damage and fatigue in composites–a personal account
  publication-title: Compos. Sci. Technol.
– volume: 28
  start-page: 189
  year: 2013
  end-page: 208
  ident: b15
  article-title: A comparative review of dimension reduction methods in approximate Bayesian computation
  publication-title: Statist. Sci.
– volume: vol. 37
  start-page: 1613
  year: 2015
  end-page: 1622
  ident: b16
  article-title: Weight uncertainty in neural network
  publication-title: Proceedings of the 32nd International Conference on Machine Learning
– volume: 493
  start-page: 5913
  year: 2020
  end-page: 5927
  ident: b47
  article-title: A unified framework for 21 cm tomography sample generation and parameter inference with progressively growing GANs
  publication-title: Mon. Not. R. Astron. Soc.
– volume: 40
  start-page: 1673
  year: 2009
  end-page: 1684
  ident: b66
  article-title: Quantification of uncertainty modelling in stochastic analysis of FRP composites
  publication-title: Composites A
– volume: 28
  start-page: 1671
  year: 2020
  end-page: 1706
  ident: b48
  article-title: Dying ReLU and initialization: Theory and numerical examples
  publication-title: Commun. Comput. Phys.
– start-page: 1184
  year: 2018
  end-page: 1193
  ident: b26
  article-title: Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning
  publication-title: International Conference on Machine Learning
– volume: 94
  year: 2020
  ident: b65
  article-title: Deep neural network model with Bayesian hyperparameter optimization for prediction of NOx at transient conditions in a diesel engine
  publication-title: Eng. Appl. Artif. Intell.
– start-page: 1319
  year: 2013
  end-page: 1327
  ident: b32
  article-title: Maxout networks
  publication-title: Proceedings of the 30th International Conference on Machine Learning, Vol. 28
– volume: 5
  start-page: 246
  year: 2017
  end-page: 255
  ident: b71
  article-title: On the safety of machine learning: Cyber-physical systems, decision sciences, and data products
  publication-title: Big Data
– reference: Wang, H., Bai, X., Tan, J., 2020. Uncertainty quantification of bearing remaining useful life based on convolutional neural network. In: 2020 IEEE Symposium Series on Computational Intelligence. SSCI. pp. 2893–2900.
– reference: Jia, S., Yue, Y., Yang, Z., Pei, X., Wang, Y., 2020. Travelling modes recognition via Bayes neural network with Bayes by backprop algorithm. In: CICTP 2020. pp. 3994–4004.
– volume: 148
  start-page: 45
  year: 2019
  end-page: 54
  ident: b62
  article-title: Performance of machine learning techniques in the detection of financial frauds
  publication-title: Procedia Comput. Sci.
– year: 2016
  ident: b31
  article-title: Deep Learning
– year: 1995
  ident: b70
  article-title: Python Reference Manual
– year: 2015
  ident: b1
  article-title: TensorFlow: Large-scale machine learning on heterogeneous systems
– reference: .
– volume: 100
  year: 2021
  ident: b3
  article-title: A new hybrid model for wind speed forecasting combining long short-term memory neural network, decomposition methods and grey wolf optimizer
  publication-title: Appl. Soft Comput.
– volume: 74
  start-page: 419
  year: 2012
  end-page: 474
  ident: b28
  article-title: Constructing summary statistics for approximate Bayesian computation: Semi-automatic approximate Bayesian computation
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
– reference: Levy, D., Sohl-dickstein, J., Hoffman, M., 2018. Generalizing Hamiltonian Monte Carlo with neural networks. In: ICLR 2018 Conference.
– volume: 23
  start-page: 535
  year: 2013
  end-page: 549
  ident: b8
  article-title: Likelihood-free parallel tempering
  publication-title: Stat. Comput.
– volume: 45
  start-page: 1942
  year: 2020
  end-page: 1952
  ident: b67
  article-title: Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions
  publication-title: Neuropsychopharmacology
– volume: 194
  start-page: 1557
  year: 2005
  end-page: 1579
  ident: b21
  article-title: Reliability estimation for dynamical systems subject to stochastic excitation using subset simulation with splitting
  publication-title: Comput. Methods Appl. Mech. Engrg.
– year: 1812
  ident: b44
  article-title: Théorie Analytique Des Probabilités
– year: 2017
  ident: b27
  article-title: ABCpy: A high-performance computing perspective to approximate Bayesian computation
– start-page: 1310
  year: 2013
  end-page: 1318
  ident: b57
  article-title: On the difficulty of training recurrent neural networks
  publication-title: International Conference on Machine Learning
– volume: 5
  start-page: 603
  year: 1991
  ident: 10.1016/j.engappai.2021.104511_b17
  article-title: BayesIan back-propagation
  publication-title: Complex Syst.
– year: 1996
  ident: 10.1016/j.engappai.2021.104511_b30
– volume: 126
  start-page: 325
  year: 2019
  ident: 10.1016/j.engappai.2021.104511_b2
  article-title: Digital currency forecasting with chaotic meta-heuristic bio-inspired signal processing techniques
  publication-title: Chaos Solitons Fractals
  doi: 10.1016/j.chaos.2019.07.011
– volume: 5
  start-page: 127
  year: 1943
  ident: 10.1016/j.engappai.2021.104511_b53
  article-title: A logical calculus of ideas immanent in nervous activity
  publication-title: Bull. Math. Biophys.
  doi: 10.1007/BF02478259
– volume: 12
  issue: 4
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b34
  article-title: A review of approximate Bayesian computation methods via density estimation: Inference for simulator-models
  publication-title: WIREs Comput. Stat.
  doi: 10.1002/wics.1486
– volume: 110
  start-page: 457
  issue: 3
  year: 2021
  ident: 10.1016/j.engappai.2021.104511_b38
  article-title: Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-021-05946-3
– volume: 84
  start-page: R869
  issue: 6
  year: 2019
  ident: 10.1016/j.engappai.2021.104511_b24
  article-title: Convolutional neural network for seismic impedance inversion
  publication-title: Geophysics
  doi: 10.1190/geo2018-0838.1
– ident: 10.1016/j.engappai.2021.104511_b40
  doi: 10.1061/9780784482933.343
– volume: 100
  start-page: 15324
  issue: 26
  year: 2003
  ident: 10.1016/j.engappai.2021.104511_b52
  article-title: Markov chain Monte Carlo without likelihoods
  publication-title: Proc. Natl. Acad. Sci.
  doi: 10.1073/pnas.0306899100
– volume: 73
  start-page: 23
  issue: 1
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b60
  article-title: Towards end-to-end likelihood-free inference with convolutional neural networks
  publication-title: Br. J. Math. Stat. Psychol.
  doi: 10.1111/bmsp.12159
– volume: 92–93
  start-page: 283
  year: 2012
  ident: 10.1016/j.engappai.2021.104511_b76
  article-title: BayesIan post-processor and other enhancements of Subset Simulation for estimating failure probabilities in high dimensions
  publication-title: Comput. Struct.
  doi: 10.1016/j.compstruc.2011.10.017
– volume: 74
  start-page: 419
  issue: 3
  year: 2012
  ident: 10.1016/j.engappai.2021.104511_b28
  article-title: Constructing summary statistics for approximate Bayesian computation: Semi-automatic approximate Bayesian computation
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
  doi: 10.1111/j.1467-9868.2011.01010.x
– ident: 10.1016/j.engappai.2021.104511_b74
  doi: 10.1109/SSCI47803.2020.9308463
– ident: 10.1016/j.engappai.2021.104511_b45
– volume: 19
  start-page: 277
  issue: 3
  year: 2006
  ident: 10.1016/j.engappai.2021.104511_b72
  article-title: Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2005.09.001
– volume: 14
  start-page: 1
  issue: 2
  year: 1946
  ident: 10.1016/j.engappai.2021.104511_b23
  article-title: Probability, frequency, and reasonable expectation
  publication-title: Amer. J. Phys.
  doi: 10.1119/1.1990764
– year: 1996
  ident: 10.1016/j.engappai.2021.104511_b56
– volume: vol. 37
  start-page: 1613
  year: 2015
  ident: 10.1016/j.engappai.2021.104511_b16
  article-title: Weight uncertainty in neural network
– year: 1961
  ident: 10.1016/j.engappai.2021.104511_b39
– ident: 10.1016/j.engappai.2021.104511_b64
– volume: 493
  start-page: 5913
  issue: 4
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b47
  article-title: A unified framework for 21 cm tomography sample generation and parameter inference with progressively growing GANs
  publication-title: Mon. Not. R. Astron. Soc.
  doi: 10.1093/mnras/staa523
– ident: 10.1016/j.engappai.2021.104511_b49
– year: 2017
  ident: 10.1016/j.engappai.2021.104511_b27
– volume: 16
  start-page: 263
  issue: 4
  year: 2001
  ident: 10.1016/j.engappai.2021.104511_b5
  article-title: Estimation of small failure probabilities in high dimensions by subset simulation
  publication-title: Probab. Eng. Mech.
  doi: 10.1016/S0266-8920(01)00019-4
– volume: 14
  issue: 5
  year: 2013
  ident: 10.1016/j.engappai.2021.104511_b37
  article-title: Stochastic variational inference
  publication-title: J. Mach. Learn. Res.
– volume: 94
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b65
  article-title: Deep neural network model with Bayesian hyperparameter optimization for prediction of NOx at transient conditions in a diesel engine
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2020.103761
– volume: 60
  start-page: 34
  year: 2012
  ident: 10.1016/j.engappai.2021.104511_b4
  article-title: Automatic speech recognition: a review
  publication-title: Int. J. Comput. Appl.
– volume: 70
  start-page: 361
  year: 2015
  ident: 10.1016/j.engappai.2021.104511_b20
  article-title: BayesIan model selection and parameter estimation for fatigue damage progression models in composites
  publication-title: Int. J. Fatigue
  doi: 10.1016/j.ijfatigue.2014.08.003
– ident: 10.1016/j.engappai.2021.104511_b18
  doi: 10.1109/IJCNN.2018.8489113
– volume: 53
  start-page: 370
  year: 1763
  ident: 10.1016/j.engappai.2021.104511_b9
  article-title: An essay towards solving a problem in the doctrine of chances
  publication-title: Phil. Trans. R. Soc. London
– volume: 5
  start-page: 246
  issue: 3
  year: 2017
  ident: 10.1016/j.engappai.2021.104511_b71
  article-title: On the safety of machine learning: Cyber-physical systems, decision sciences, and data products
  publication-title: Big Data
  doi: 10.1089/big.2016.0051
– start-page: A1339
  issue: 3
  year: 2014
  ident: 10.1016/j.engappai.2021.104511_b19
  article-title: Approximate Bayesian computation by subset simulation
  publication-title: SIAM J. Sci. Comput.
  doi: 10.1137/130932831
– start-page: 2348
  year: 2011
  ident: 10.1016/j.engappai.2021.104511_b33
  article-title: Practical variational inference for neural networks
– volume: vol. 37
  start-page: 1861
  year: 2015
  ident: 10.1016/j.engappai.2021.104511_b36
  article-title: Probabilistic backpropagation for scalable learning of Bayesian neural networks
– volume: 28
  start-page: 189
  issue: 2
  year: 2013
  ident: 10.1016/j.engappai.2021.104511_b15
  article-title: A comparative review of dimension reduction methods in approximate Bayesian computation
  publication-title: Statist. Sci.
  doi: 10.1214/12-STS406
– volume: 521
  start-page: 452
  issue: 7553
  year: 2015
  ident: 10.1016/j.engappai.2021.104511_b29
  article-title: Probabilistic machine learning and artificial intelligence
  publication-title: Nature
  doi: 10.1038/nature14541
– start-page: 8024
  year: 2019
  ident: 10.1016/j.engappai.2021.104511_b58
  article-title: Pytorch: An imperative style, high-performance deep learning library
– volume: 28
  start-page: 1671
  issue: 5
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b48
  article-title: Dying ReLU and initialization: Theory and numerical examples
  publication-title: Commun. Comput. Phys.
  doi: 10.4208/cicp.OA-2020-0165
– volume: 28
  start-page: 819
  issue: 4
  year: 2018
  ident: 10.1016/j.engappai.2021.104511_b59
  article-title: A rare event approach to high-dimensional approximate Bayesian computation
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-017-9764-4
– year: 2017
  ident: 10.1016/j.engappai.2021.104511_b13
– volume: 29
  start-page: 183
  issue: 3
  year: 2007
  ident: 10.1016/j.engappai.2021.104511_b6
  article-title: Application of subset simulation methods to reliability benchmark problems
  publication-title: Struct. Saf.
  doi: 10.1016/j.strusafe.2006.07.008
– volume: 68
  start-page: 2585
  issue: 13
  year: 2008
  ident: 10.1016/j.engappai.2021.104511_b68
  article-title: Damage and fatigue in composites–a personal account
  publication-title: Compos. Sci. Technol.
  doi: 10.1016/j.compscitech.2008.04.042
– volume: 40
  start-page: 1673
  issue: 11
  year: 2009
  ident: 10.1016/j.engappai.2021.104511_b66
  article-title: Quantification of uncertainty modelling in stochastic analysis of FRP composites
  publication-title: Composites A
  doi: 10.1016/j.compositesa.2009.08.020
– volume: 100
  year: 2021
  ident: 10.1016/j.engappai.2021.104511_b3
  article-title: A new hybrid model for wind speed forecasting combining long short-term memory neural network, decomposition methods and grey wolf optimizer
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2020.106996
– year: 1993
  ident: 10.1016/j.engappai.2021.104511_b55
– year: 1995
  ident: 10.1016/j.engappai.2021.104511_b70
– year: 2016
  ident: 10.1016/j.engappai.2021.104511_b31
– volume: 26
  start-page: 331
  issue: 2
  year: 2011
  ident: 10.1016/j.engappai.2021.104511_b63
  article-title: Modified Metropolis–Hastings algorithm with reduced chain correlation for efficient subset simulation
  publication-title: Probab. Eng. Mech.
  doi: 10.1016/j.probengmech.2010.08.007
– year: 2015
  ident: 10.1016/j.engappai.2021.104511_b1
– start-page: 1319
  year: 2013
  ident: 10.1016/j.engappai.2021.104511_b32
  article-title: Maxout networks
– volume: 2018
  year: 2018
  ident: 10.1016/j.engappai.2021.104511_b73
  article-title: Deep learning for computer vision: a brief review
  publication-title: Comput. Intell. Neurosci.
  doi: 10.1155/2018/7068349
– volume: 3
  start-page: 173
  issue: 1
  year: 2011
  ident: 10.1016/j.engappai.2021.104511_b7
  article-title: Machine learning methods for spam e-mail classification
  publication-title: Int. J. Comput. Sci. Inf. Technol.
– year: 1812
  ident: 10.1016/j.engappai.2021.104511_b44
– volume: 45
  start-page: 1942
  issue: 11
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b67
  article-title: Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions
  publication-title: Neuropsychopharmacology
  doi: 10.1038/s41386-020-0776-y
– volume: In Press
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b12
  article-title: Utilizing uncertainty information in remaining useful life estimation via Bayesian neural networks and Hamiltonian Monte Carlo
  publication-title: J. Manuf. Syst.
– volume: 194
  start-page: 1557
  issue: 12
  year: 2005
  ident: 10.1016/j.engappai.2021.104511_b21
  article-title: Reliability estimation for dynamical systems subject to stochastic excitation using subset simulation with splitting
  publication-title: Comput. Methods Appl. Mech. Engrg.
  doi: 10.1016/j.cma.2004.05.028
– volume: 323
  start-page: 533
  year: 1986
  ident: 10.1016/j.engappai.2021.104511_b61
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
  doi: 10.1038/323533a0
– volume: 17
  start-page: 825
  issue: 7
  year: 2010
  ident: 10.1016/j.engappai.2021.104511_b11
  article-title: BayesIan system identification based on probability logic
  publication-title: Struct. Control Health Monit.
  doi: 10.1002/stc.424
– volume: 14
  start-page: 257
  issue: 3
  year: 2001
  ident: 10.1016/j.engappai.2021.104511_b43
  article-title: BayesIan approach for neural networks—review and case studies
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(00)00098-8
– year: 2021
  ident: 10.1016/j.engappai.2021.104511_b35
– volume: 27
  start-page: 1595
  issue: 4
  year: 2017
  ident: 10.1016/j.engappai.2021.104511_b41
  article-title: Learning summary statistic for approximate Bayesian computation via deep neural network
  publication-title: Statist. Sinica
– volume: 148
  start-page: 45
  year: 2019
  ident: 10.1016/j.engappai.2021.104511_b62
  article-title: Performance of machine learning techniques in the detection of financial frauds
  publication-title: Procedia Comput. Sci.
  doi: 10.1016/j.procs.2019.01.007
– start-page: 1184
  year: 2018
  ident: 10.1016/j.engappai.2021.104511_b26
  article-title: Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning
– volume: 23
  start-page: 535
  issue: 4
  year: 2013
  ident: 10.1016/j.engappai.2021.104511_b8
  article-title: Likelihood-free parallel tempering
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-012-9328-6
– volume: 96
  start-page: 983
  issue: 4
  year: 2009
  ident: 10.1016/j.engappai.2021.104511_b10
  article-title: Adaptive approximate Bayesian computation
  publication-title: Biometrika
  doi: 10.1093/biomet/asp052
– volume: 22
  start-page: 1009
  issue: 5
  year: 2012
  ident: 10.1016/j.engappai.2021.104511_b25
  article-title: An adaptive sequential Monte Carlo method for approximate Bayesian computation
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-011-9271-y
– year: 1992
  ident: 10.1016/j.engappai.2021.104511_b54
– volume: 131
  year: 2020
  ident: 10.1016/j.engappai.2021.104511_b75
  article-title: BayesIan neural networks for flight trajectory prediction and safety assessment
  publication-title: Decis. Support Syst.
  doi: 10.1016/j.dss.2020.113246
– volume: 4
  start-page: 448
  issue: 3
  year: 1992
  ident: 10.1016/j.engappai.2021.104511_b50
  article-title: A practical Bayesian framework for backpropagation networks
  publication-title: Neural Comput.
  doi: 10.1162/neco.1992.4.3.448
– year: 2007
  ident: 10.1016/j.engappai.2021.104511_b69
– ident: 10.1016/j.engappai.2021.104511_b46
– ident: 10.1016/j.engappai.2021.104511_b42
– volume: 20
  start-page: 63
  year: 2010
  ident: 10.1016/j.engappai.2021.104511_b14
  article-title: Non-linear regression models for approximate Bayesian computation
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-009-9116-0
– year: 2015
  ident: 10.1016/j.engappai.2021.104511_b22
– start-page: 1310
  year: 2013
  ident: 10.1016/j.engappai.2021.104511_b57
  article-title: On the difficulty of training recurrent neural networks
– start-page: 1167
  year: 2012
  ident: 10.1016/j.engappai.2021.104511_b51
  article-title: Approximate Bayesian computational methods
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-011-9288-2
SSID ssj0003846
Score 2.5205214
Snippet Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 104511
SubjectTerms Approximate Bayesian Computation
Bayesian Neural Network
Gradient-free training
Non-parametric formulation
Subset Simulation
Uncertainty quantification
Title Uncertainty quantification in Neural Networks by Approximate Bayesian Computation: Application to fatigue in composite materials
URI https://dx.doi.org/10.1016/j.engappai.2021.104511
Volume 107
WOSCitedRecordID wos000747080100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-6769
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003846
  issn: 0952-1976
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlAMX3qgtD-2BW-Xit9e9paUIKogQtCg3a7Net64ipyR2ld74h_wlZvZhO1BUEOJiWWut1_H3xTs7O_MNIS9jxhkYHtKJXA4LlIDFDoNZ2WG-4EHou7mrxKq_vE_GYzaZpB8Hg-82F-ZyllQVW63Si_8KNbQB2Jg6-xdwtzeFBjgH0OEIsMPxj4A_ARjVNj-Y118broOBuI1pRDEOQGWso7-XaH2OUFZ8VYLpKnf2-ZVUaZW62kMb-jHq9rnRWi3g7LRReiMYk46BXxgIW-vft-bt7_QOd_qb5Sr-YKGeTZUN6SmD9l3cah_fs37uo6bj8sFZycWZuv56rrOOqkbOfnu53_dDgxf2vbm66yde2MQB4_7w_Z_cH21eThcEpZ2bvuOliRHZ1p92lgQOBvSufft1yd1f5hHt0jjfldUpvBte7sLQHu6HR2ZqWNfo_owD4niwgEZNxPgW2fCTKGVDsjF6dzg5ao2DgOncMfuAvaT160e73l7q2UDH98lds3ihI026B2Qgq4fknlnIUDNNLKHJ1gqxbY_Itx4t6TotaVlRTUtqaUmnV7RHS2ppSXu03KM9UtJ6Tg0p8XYtKWlLysfk5M3h8cFbx1T_cEQQu7UjWO6lkUxR_mkqQyEwBTvkac4CgYVlI7eAxb70Ci6kKwqRiFigWp9kcZ7IwguekGE1r-QmoWEShTxGQe6Ah_40ZH4go5xPE8nCUEZsi0T2HWfCSONjhZZZZmMgzzOLTYbYZBqbLfKq7XehxWFu7JFaCDNj4mrTNQPm3dB3-x_6PiV3uj_PMzKsF418Tm6Ly7pcLl4Ykv4Am_DTBg
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Uncertainty+quantification+in+Neural+Networks+by+Approximate+Bayesian+Computation%3A+Application+to+fatigue+in+composite+materials&rft.jtitle=Engineering+applications+of+artificial+intelligence&rft.au=Fern%C3%A1ndez%2C+Juan&rft.au=Chiach%C3%ADo%2C+Manuel&rft.au=Chiach%C3%ADo%2C+Juan&rft.au=Mu%C3%B1oz%2C+Rafael&rft.date=2022-01-01&rft.pub=Elsevier+Ltd&rft.issn=0952-1976&rft.eissn=1873-6769&rft.volume=107&rft_id=info:doi/10.1016%2Fj.engappai.2021.104511&rft.externalDocID=S0952197621003596
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-1976&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-1976&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-1976&client=summon