Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/28745
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, B | - |
dc.contributor.author | Sui, W | - |
dc.contributor.author | Huang, Z | - |
dc.contributor.author | Li, M | - |
dc.contributor.author | Qi, M | - |
dc.date.accessioned | 2024-04-10T19:16:26Z | - |
dc.date.available | 2024-04-10T19:16:26Z | - |
dc.date.issued | 2024-04-04 | - |
dc.identifier | ORCiD: Baobing Zhang https://orcid.org/0009-0009-8330-239X | - |
dc.identifier | ORCiD: Zhengwen Huang https://orcid.org/0000-0003-2426-242X | - |
dc.identifier | ORCiD: Maozhen Li https://orcid.org/0000-0002-0820-5487 | - |
dc.identifier | 127645 | - |
dc.identifier.citation | Zhang, B. et al. (2024) 'Normalizing flow based uncertainty estimation for deep regression analysis', Neurocomputing, 585, 127645, pp. 1 - 9. doi: 10.1016/j.neucom.2024.127645. | en_US |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/28745 | - |
dc.description | Data availability: Data will be made available on request. | en_US |
dc.description.abstract | Uncertainty estimation is a critical component of building safe and reliable machine learning models. Accurate estimation of uncertainties is essential for identifying and mitigating potential risks and ensuring that machine learning systems operate reliably in real-world scenarios. Various approaches, such as ensemble and Bayesian neural networks have been developed by sampling probability predictions from submodels, which is computationally expensive. At present, these techniques are incapable of precisely delineating the boundary separating in-distribution (ID) and out-of-distribution (OOD) data. To fill up this research gap, this paper presents a normalizing flow based framework to directly predict parameters of prior distributions over the probability with a neural network, the proposed model is able to effectively differentiate between ID and OOD data in regression problems. The posterior distributions learned by the model precisely represent uncertainties for OOD data based solely on ID data, without the need for OOD data during training. This approach has shown promising results in a number of applications, including image depth estimation and image adversarial attacks. | en_US |
dc.format.extent | 1 - 9 | - |
dc.language | English | - |
dc.language.iso | en_US | en_US |
dc.publisher | Elsevier | en_US |
dc.rights | Copyright © 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/). | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | regression | en_US |
dc.subject | predictive uncertainty | en_US |
dc.subject | normalizing flow | en_US |
dc.subject | probabilistic modeling | en_US |
dc.subject | adversarial robustness | en_US |
dc.subject | calibration | en_US |
dc.title | Normalizing flow based uncertainty estimation for deep regression analysis | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1016/j.neucom.2024.127645 | - |
dc.relation.isPartOf | Neurocomputing | - |
pubs.publication-status | Published | - |
pubs.volume | 585 | - |
dc.identifier.eissn | 1872-8286 | - |
dc.rights.license | https://creativecommons.org/licenses/by/4.0/legalcode.en | - |
dc.rights.holder | The Author(s) | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/). | 2.39 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License