Global and Local Interpretability of Belief Rule Base

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The rapid adoption of artificial intelligence in automating human-centred tasks has accentuated the importance of interpretable decisions. The Belief-Rule-Base (BRB) is a hybrid expert system that can accommodate human knowledge and capture nonlinear causal relationships as well as uncertainty. This paper presents the strategy to interpret BRB locally for a single instance to understand the decision-making process by the importance of activated rules and attributes and globally to understand most important rules and attributes in an entire rule base.

Bibliographical metadata

Original languageEnglish
Title of host publicationProceedings of FLINS2020
PublisherWorld Scientific Publishing Co
Publication statusAccepted/In press - 8 Mar 2020
EventThe 14th International Conference on Robotics and Artificial Intelligence - Cologne, Germany
Event duration: 30 Sep 20203 Oct 2020
https://www.hrm-bildung.de/flins2020/

Conference

ConferenceThe 14th International Conference on Robotics and Artificial Intelligence
Abbreviated titleFLINS 2020
CountryGermany
CityCologne
Period30/09/203/10/20
Internet address