City Research Online

Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks

Confalonieri, R., Weyde, T. ORCID: 0000-0001-8028-9905, Besold, T. R. and Moscoso del Prado Martín, F. (2020). Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks. In: 24th European Conference on Artificial Intelligence (ECAI 2020). Frontiers in Artificial Intelligence and Applications, 325. (pp. 2457-2464). IOS Press. ISBN 978-1-64368-100-9

Abstract

Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the `how' and `why' of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the understandability of global explanations from the users' perspective. In this paper, we show how ontologies help the understandability of global post-hoc explanations, presented in the form of symbolic models. In particular, we build on Trepan, an algorithm that explains artificial neural networks by means of decision trees, and we extend it to include ontologies modeling domain knowledge in the process of generating explanations. We present the results of a user study that measures the understandability of decision trees using a syntactic complexity measure, and through time and accuracy of responses as well as reported user confidence and understandability. The user study considers domains where explanations are critical, namely, in finance and medicine. The results show that decision trees generated with our algorithm, taking into account domain knowledge, are more understandable than those generated by standard Trepan without the use of ontologies.

Publication Type: Conference or Workshop Item (UNSPECIFIED)
Additional Information: This is an Open Access chapter made available under a Creative Commons Attribution NonCommercial Licence. (CC-BY-NC)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
Date Deposited: 18 Sep 2020 13:58
URI: https://openaccess.city.ac.uk/id/eprint/24630
[img]
Preview
Text - Published Version
Available under License Creative Commons Attribution Non-commercial.

Download (416kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login