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:
|insight_publication.pdf||453.81 kB||Adobe 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:||CBR; Explanation; Artificial neural networks; XAI; Deep 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
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.