Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Potter, Michael, Jun, Miru
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913187614425088
author Potter, Michael
Jun, Miru
author_facet Potter, Michael
Jun, Miru
contents We implement a Bayesian inference process for Neural Networks to model the time to failure of highly reliable weapon systems with interval-censored data and time-varying covariates. We analyze and benchmark our approach, LaplaceNN, on synthetic and real datasets with standard classification metrics such as Receiver Operating Characteristic (ROC) Area Under Curve (AUC) Precision-Recall (PR) AUC, and reliability curve visualizations.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10494
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?
Potter, Michael
Jun, Miru
Machine Learning
Applications
We implement a Bayesian inference process for Neural Networks to model the time to failure of highly reliable weapon systems with interval-censored data and time-varying covariates. We analyze and benchmark our approach, LaplaceNN, on synthetic and real datasets with standard classification metrics such as Receiver Operating Characteristic (ROC) Area Under Curve (AUC) Precision-Recall (PR) AUC, and reliability curve visualizations.
title Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?
topic Machine Learning
Applications
url https://arxiv.org/abs/2312.10494