The reviewed record of science sign in
Pith

arxiv: 2103.12141 · v1 · pith:Y7RQFALA · submitted 2021-03-22 · cs.LG · cs.SY· eess.SY

Performance Bounds for Neural Network Estimators: Applications in Fault Detection

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:Y7RQFALArecord.jsonopen to challenge →

classification cs.LG cs.SYeess.SY
keywords neuralnetworkboundsdetectorinputtuningunderaccomplish
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.