Global and Local Interpretability of Belief Rule Base

Swati Sachan; Jian-Bo Yang; Dong-Ling Xu

doi:10.1142/9789811223334_0009

Global and Local Interpretability of Belief Rule Base

Swati Sachan, Jian-Bo Yang, Dong-Ling Xu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

67 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of FLINS2020
Publisher	World Scientific Publishing Co
DOIs	https://doi.org/10.1142/9789811223334_0009
Publication status	Published - 8 Mar 2020
Event	The 14th International Conference on Robotics and Artificial Intelligence - Cologne, Germany Duration: 30 Sep 2020 → 3 Oct 2020 https://www.hrm-bildung.de/flins2020/

Conference

Conference	The 14th International Conference on Robotics and Artificial Intelligence
Abbreviated title	FLINS 2020
Country/Territory	Germany
City	Cologne
Period	30/09/20 → 3/10/20
Internet address	https://www.hrm-bildung.de/flins2020/

Keywords

Interpretability
Decision
Rule base

Access to Document

10.1142/9789811223334_0009

pdfCamera_copy_swati_flintAccepted author manuscript, 438 KB

Cite this

@inproceedings{703bef70f68b48eea56d7edab71a3217,

title = "Global and Local Interpretability of Belief Rule Base",

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.",

keywords = "Interpretability, Decision, Rule base",

author = "Swati Sachan and Jian-Bo Yang and Dong-Ling Xu",

year = "2020",

month = mar,

day = "8",

doi = "10.1142/9789811223334_0009",

language = "English",

booktitle = "Proceedings of FLINS2020",

publisher = "World Scientific Publishing Co",

address = "United States",

note = "The 14th International Conference on Robotics and Artificial Intelligence, FLINS 2020 ; Conference date: 30-09-2020 Through 03-10-2020",

url = "https://www.hrm-bildung.de/flins2020/",

}

TY - GEN

T1 - Global and Local Interpretability of Belief Rule Base

AU - Sachan, Swati

AU - Yang, Jian-Bo

AU - Xu, Dong-Ling

PY - 2020/3/8

Y1 - 2020/3/8

N2 - 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.

AB - 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.

KW - Interpretability

KW - Decision

KW - Rule base

U2 - 10.1142/9789811223334_0009

DO - 10.1142/9789811223334_0009

M3 - Conference contribution

BT - Proceedings of FLINS2020

PB - World Scientific Publishing Co

T2 - The 14th International Conference on Robotics and Artificial Intelligence

Y2 - 30 September 2020 through 3 October 2020

ER -

Global and Local Interpretability of Belief Rule Base

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this