The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning

Files in This Item:
File Description SizeFormat 
insight_publication.pdf718.3 kBAdobe PDFDownload
Title: The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning
Authors: Keane, Mark T.Kenny, Eoin M.
Permanent link: http://hdl.handle.net/10197/11071
Date: 11-Aug-2019
Online since: 2019-09-10T11:56:04Z
Abstract: The notion of twin-systems is proposed to address the eXplainable AI (XAI) problem, where an uninterpretable black-box system is mapped to a white-box “twin” that is more interpretable. In this short paper, we overview very recent work that advances a generic solution to the XAI problem, the so-called twin-system approach. The most popular twinning in the literature is that between an Artificial Neural Networks (ANN1) as a black box and Case Based Reasoning (CBR) system as a white-box, where the latter acts as an interpretable proxy for the former. We outline how recent work reviving this idea has applied it to deep learning methods. Furthermore, we detail the many fruitful directions in which this work may be taken; such as, determining the most (i) accurate feature-weighting methods to be used, (ii) appropriate deployments for explanatory cases, (iii) useful cases of explanatory value to users.
Funding Details: Department of Agriculture, Food and the Marine
Science Foundation Ireland
Type of material: Conference Publication
Keywords: Recommender SystemsArtificial intelligenceTwin systems
Other versions: https://sites.google.com/view/xai2019/home
https://www.ijcai19.org/
Language: en
Status of Item: Peer reviewed
Is part of: Miller, T., Weber, R., Magazzeni, D., Proceedings of the IJCAI 2019 Workshop on Explainable Artificial Intelligence
Conference Details: IJCAI 2019 Workshop on Explainable Artificial Intelligence (XAI). Macau, China, 11 August 2019
Appears in Collections:Computer Science Research Collection
Insight Research Collection

Show full item record

Google ScholarTM

Check


This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.