How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

Files in This Item:
Access to this item has been restricted by the copyright holder until:2020-08-06
File Description SizeFormat 
insight_publication.pdf453.81 kBAdobe PDF    Request a copy
Title: How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems
Authors: Keane, Mark T.Kenny, Eoin M.
Permanent link: http://hdl.handle.net/10197/11070
Date: 9-Aug-2019
Online since: 2019-09-10T11:27:19Z
Abstract: This paper proposes a theoretical analysis of one approach to the eXplainable AI (XAI) problem, using post-hoc explanation-by-example, that relies on the twinning of artificial neural networks (ANNs) with case-based reasoning (CBR) systems; so-called ANN-CBR twins. It surveys these systems to advance a new theoretical interpretation of previous work and define a road map for CBR’s further role in XAI. A systematic survey of 1,102 papers was conducted to identify a fragmented literature on this topic and trace its influence to more recent work involving deep neural networks (DNNs). The twin-systems approach is advanced as one possible coherent, generic solution to the XAI problem. The paper concludes by road-mapping future directions for this XAI solution, considering (i) further tests of feature-weighting techniques, (ii) how explanatory cases might be deployed (e.g., in counterfactuals, a fortori cases), and (iii) the unwelcome, much-ignored issue of user evaluation.
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Publisher: Springer
Series/Report no.: Lecture Notes in Computer Science (LNCS, volume 11680)
Copyright (published version): 2019 Springer
Keywords: CBRExplanationArtificial neural networksXAIDeep learning
DOI: 10.1007/978-3-030-29249-2_11
Language: en
Status of Item: Peer reviewed
Is part of: Bach, K., Marling, C. (eds.). Case-Based Reasoning Research and Development: 27th International Conference, ICCBR 2019 Otzenhausen, Germany, September 8-12, 2019 Proceedings
ISBN: 978-3-030-29248-5
Appears in Collections:Computer Science Research Collection
Insight Research Collection

Show full item record

Google ScholarTM

Check

Altmetric


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.