Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?
Machine Learning
2024-01-09 v2 Applications
Abstract
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.
Cite
@article{arxiv.2312.10494,
title = {Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance?},
author = {Michael Potter and Miru Jun},
journal= {arXiv preprint arXiv:2312.10494},
year = {2024}
}