Keane, Mark T.Mark T.KeaneKenny, Eoin M.Eoin M.Kenny2019-09-102019-09-102019 Sprin2019-08-09978-3-030-29248-5http://hdl.handle.net/10197/11070This 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.enThis is an Accepted Manuscript of a book chapter published by Routledge in nternational Conference on Case-Based Reasoning on 09 August 2019, available online: https://doi.org/10.1007/978-3-030-29249-2_11.CBRExplanationArtificial neural networksXAIDeep learningConference Publication10.1007/978-3-030-29249-2_112019-08-29https://creativecommons.org/licenses/by-nc-nd/3.0/ie/