Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Strategies for Safety Goal Decomposition for Neural Networks

Publication

Strategies for Safety Goal Decomposition for Neural Networks

Schwalbe, Gesina; Schels, Martin (2020): Strategies for Safety Goal Decomposition for Neural Networks, in: Bamberg: Otto-Friedrich-Universität, doi: 10.20378/irb-47274.

Details

Faculty/Chair
Faculty/Professorship
Author
Schwalbe, Gesina
Schels, Martin
Corporate Body
ACM Computer Science in Cars Symposium (CSCS), 3, 2019, Kaiserslautern
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2020
Pages
3
Source/Other editions
3rd ACM Computer Science in Cars Symposium – Future Challenges in Artificial Intelligence & Security for Autonomous Vehicles / German Chapter of the ACM e.V. : München, S. 3
Year of first publication
2019
Language
English
DOI
Licence
URL
URN
Abstract

Neural networks (NNs) have become a key technology for solving highly complex tasks, and require integration into future safety argumentations. New safety relevant aspects introduced by NN based algorithms are: representativity of test cases, robustness, inner representation and logic, and failure detection for NNs. In this paper, a general argumentation structure for safety cases respecting these four aspects is proposed together with possible sources of evidence.

GND Keywords
Neuronales Netz
Beweisführung
Dekomposition
Sicherheit
Keywords
neural network
safety argumentation
safety goal decomposition
DDC Classification
004 Computer science
RVK Classification
ST 301
Type
Conferenceobject
URI
Activation date
2020-07-03

Permalink: https://fis.uni-bamberg.de/handle/uniba/47274 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.