Performance Bounds for Neural Network Estimators: Applications in Fault Detection
Machine Learning
2021-03-24 v1 Systems and Control
Systems and Control
Abstract
We exploit recent results in quantifying the robustness of neural networks to input variations to construct and tune a model-based anomaly detector, where the data-driven estimator model is provided by an autoregressive neural network. In tuning, we specifically provide upper bounds on the rate of false alarms expected under normal operation. To accomplish this, we provide a theory extension to allow for the propagation of multiple confidence ellipsoids through a neural network. The ellipsoid that bounds the output of the neural network under the input variation informs the sensitivity - and thus the threshold tuning - of the detector. We demonstrate this approach on a linear and nonlinear dynamical system.
Cite
@article{arxiv.2103.12141,
title = {Performance Bounds for Neural Network Estimators: Applications in Fault Detection},
author = {Navid Hashemi and Mahyar Fazlyab and Justin Ruths},
journal= {arXiv preprint arXiv:2103.12141},
year = {2021}
}