How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins
It addresses the explainability problem in AI for users needing transparent neural network decisions, but it is incremental as it builds on existing fragmented literature.
This paper surveys the use of ANN-CBR twins for post-hoc explanation-by-example in XAI, based on a systematic review of over 1100 papers, and argues that this approach offers a coherent, generic solution to the XAI problem.
This paper surveys an approach to the XAI problem, using post-hoc explanation by example, that hinges on twinning Artificial Neural Networks (ANNs) with Case-Based Reasoning (CBR) systems, so-called ANN-CBR twins. A systematic survey of 1100+ papers was carried out to identify the fragmented literature on this topic and to trace it influence through to more recent work involving Deep Neural Networks (DNNs). The paper argues that this twin-system approach, especially using ANN-CBR twins, presents one possible coherent, generic solution to the XAI problem (and, indeed, XCBR problem). The paper concludes by road-mapping some future directions for this XAI solution involving (i) further tests of feature-weighting techniques, (iii) explorations of how explanatory cases might best be deployed (e.g., in counterfactuals, near-miss cases, a fortori cases), and (iii) the raising of the unwelcome and, much ignored, issue of human user evaluation.