Saved in:
Bibliographic Details
Main Authors: Hashemi, Vahid, Křetínský, Jan, Rieder, Sabine, Schön, Torsten, Vorhoff, Jan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.06051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910641076305920
author Hashemi, Vahid
Křetínský, Jan
Rieder, Sabine
Schön, Torsten
Vorhoff, Jan
author_facet Hashemi, Vahid
Křetínský, Jan
Rieder, Sabine
Schön, Torsten
Vorhoff, Jan
contents Since neural networks can make wrong predictions even with high confidence, monitoring their behavior at runtime is important, especially in safety-critical domains like autonomous driving. In this paper, we combine ideas from previous monitoring approaches based on observing the activation values of hidden neurons. In particular, we combine the Gaussian-based approach, which observes whether the current value of each monitored neuron is similar to typical values observed during training, and the Outside-the-Box monitor, which creates clusters of the acceptable activation values, and, thus, considers the correlations of the neurons' values. Our experiments evaluate the achieved improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces
Hashemi, Vahid
Křetínský, Jan
Rieder, Sabine
Schön, Torsten
Vorhoff, Jan
Machine Learning
Since neural networks can make wrong predictions even with high confidence, monitoring their behavior at runtime is important, especially in safety-critical domains like autonomous driving. In this paper, we combine ideas from previous monitoring approaches based on observing the activation values of hidden neurons. In particular, we combine the Gaussian-based approach, which observes whether the current value of each monitored neuron is similar to typical values observed during training, and the Outside-the-Box monitor, which creates clusters of the acceptable activation values, and, thus, considers the correlations of the neurons' values. Our experiments evaluate the achieved improvement.
title Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces
topic Machine Learning
url https://arxiv.org/abs/2410.06051