Lab Conditions for Research on Explainable Automated Decisions

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

Abstract

Artificial neural networks are being proposed for automated decision making under uncertainty in many visionary contexts, including high-stake tasks such as navigating autonomous cars through dense traffic. Against this background, it is imperative that the decision making entities meet central societal desiderata regarding dependability, perspicuity, explainability, and robustness. Decision making problems under uncertainty are typically captured formally as variations of Markov decision processes (MDPs). This paper discusses a set of natural and easy-to-control abstractions, based on the Racetrack benchmarks and extensions thereof, that altogether connect the autonomous driving challenge to the modelling world of MDPs. This is then used to study the dependability and robustness of NN-based decision entities, which in turn are based on state-of-the-art NN learning techniques. We argue that this approach can be regarded as providing laboratory conditions for a systematic, structured and extensible comparative analysis of NN behavior, of NN learning performance, as well as of NN verification and analysis techniques.

Details

OriginalspracheEnglisch
TitelTrustworthy AI – Integrating Learning, Optimization and Reasoning
Redakteure/-innenFredrik Heintz, Michela Milano, Barry O’Sullivan
Herausgeber (Verlag)Springer, Berlin [u. a.]
Seiten83-90
Seitenumfang8
ISBN (Print)978-3-030-73958-4
PublikationsstatusVeröffentlicht - 2021
Peer-Review-StatusJa

Publikationsreihe

ReiheLecture Notes in Computer Science, Volume 12641
ISSN0302-9743

Workshop

Titel1st International Workshop on Trustworthy AI – Integrating Learning, Optimization and Reasoning
KurztitelTAILOR 2020
Veranstaltungsnummer1
Beschreibungheld as a part of European Conference on Artificial Intelligence, ECAI 2020
Dauer4 - 5 September 2020
BekanntheitsgradInternationale Veranstaltung
Ortonline

Externe IDs

ORCID /0000-0002-5321-9343/work/142236756

Schlagworte