Reliable neural networks for regression uncertainty estimation. Tohme, T., Vanslette, K., & Youcef-Toumi, K. Reliability Engineering & System Safety, 229:108811, January, 2023. ![Reliable neural networks for regression uncertainty estimation [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regression uncertainty estimation based on the Bayesian Validation Metric (BVM) framework while using ensemble learning. The proposed loss reproduces maximum likelihood estimation in the limiting case. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. Experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.
@article{tohme_reliable_2023,
title = {Reliable neural networks for regression uncertainty estimation},
volume = {229},
issn = {0951-8320},
url = {https://www.sciencedirect.com/science/article/pii/S0951832022004306},
doi = {10.1016/j.ress.2022.108811},
abstract = {While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regression uncertainty estimation based on the Bayesian Validation Metric (BVM) framework while using ensemble learning. The proposed loss reproduces maximum likelihood estimation in the limiting case. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. Experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.},
language = {en},
urldate = {2022-10-29},
journal = {Reliability Engineering \& System Safety},
author = {Tohme, Tony and Vanslette, Kevin and Youcef-Toumi, Kamal},
month = jan,
year = {2023},
keywords = {Neural networks, Predictive uncertainty estimation, Regression, Reliability},
pages = {108811},
}
Downloads: 0
{"_id":"Nz84smewn8J8rRddr","bibbaseid":"tohme-vanslette-youceftoumi-reliableneuralnetworksforregressionuncertaintyestimation-2023","author_short":["Tohme, T.","Vanslette, K.","Youcef-Toumi, K."],"bibdata":{"bibtype":"article","type":"article","title":"Reliable neural networks for regression uncertainty estimation","volume":"229","issn":"0951-8320","url":"https://www.sciencedirect.com/science/article/pii/S0951832022004306","doi":"10.1016/j.ress.2022.108811","abstract":"While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regression uncertainty estimation based on the Bayesian Validation Metric (BVM) framework while using ensemble learning. The proposed loss reproduces maximum likelihood estimation in the limiting case. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. Experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.","language":"en","urldate":"2022-10-29","journal":"Reliability Engineering & System Safety","author":[{"propositions":[],"lastnames":["Tohme"],"firstnames":["Tony"],"suffixes":[]},{"propositions":[],"lastnames":["Vanslette"],"firstnames":["Kevin"],"suffixes":[]},{"propositions":[],"lastnames":["Youcef-Toumi"],"firstnames":["Kamal"],"suffixes":[]}],"month":"January","year":"2023","keywords":"Neural networks, Predictive uncertainty estimation, Regression, Reliability","pages":"108811","bibtex":"@article{tohme_reliable_2023,\n\ttitle = {Reliable neural networks for regression uncertainty estimation},\n\tvolume = {229},\n\tissn = {0951-8320},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0951832022004306},\n\tdoi = {10.1016/j.ress.2022.108811},\n\tabstract = {While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task. To address this challenge, we propose and implement a loss function for regression uncertainty estimation based on the Bayesian Validation Metric (BVM) framework while using ensemble learning. The proposed loss reproduces maximum likelihood estimation in the limiting case. A series of experiments on in-distribution data show that the proposed method is competitive with existing state-of-the-art methods. Experiments on out-of-distribution data show that the proposed method is robust to statistical change and exhibits superior predictive capability.},\n\tlanguage = {en},\n\turldate = {2022-10-29},\n\tjournal = {Reliability Engineering \\& System Safety},\n\tauthor = {Tohme, Tony and Vanslette, Kevin and Youcef-Toumi, Kamal},\n\tmonth = jan,\n\tyear = {2023},\n\tkeywords = {Neural networks, Predictive uncertainty estimation, Regression, Reliability},\n\tpages = {108811},\n}\n\n\n\n","author_short":["Tohme, T.","Vanslette, K.","Youcef-Toumi, K."],"key":"tohme_reliable_2023","id":"tohme_reliable_2023","bibbaseid":"tohme-vanslette-youceftoumi-reliableneuralnetworksforregressionuncertaintyestimation-2023","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0951832022004306"},"keyword":["Neural networks","Predictive uncertainty estimation","Regression","Reliability"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["neural networks","predictive uncertainty estimation","regression","reliability"],"search_terms":["reliable","neural","networks","regression","uncertainty","estimation","tohme","vanslette","youcef-toumi"],"title":"Reliable neural networks for regression uncertainty estimation","year":2023}