Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI
|Title:||Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI||Authors:||Kenny, Eoin M.; Keane, Mark T.||Permanent link:||http://hdl.handle.net/10197/11064||Date:||31-Jul-2019||Online since:||2019-08-29T11:38:34Z||Abstract:||In this paper, twin-systems are described to address the eXplainable artificial intelligence (XAI) problem, where a black box model is mapped to a white box “twin” that is more interpretable, with both systems using the same dataset. The framework is instantiated by twinning an artificial neural network (ANN; black box) with a case-based reasoning system (CBR; white box), and mapping the feature weights from the former to the latter to find cases that explain the ANN’s outputs. Using a novel evaluation method, the effectiveness of this twin-system approach is demonstrated by showing that nearest neighbor cases can be found to match the ANN predictions for benchmark datasets. Several feature-weighting methods are competitively tested in two experiments, including our novel, contributions-based method (called COLE) that is found to perform best. The tests consider the ”twinning” of traditional multilayer perceptron (MLP) networks and convolutional neural networks (CNN) with CBR systems. For the CNNs trained on image data, qualitative evidence shows that cases provide plausible explanations for the CNN’s classifications.||Funding Details:||Science Foundation Ireland||Type of material:||Conference Publication||Start page:||2708||End page:||2715||Copyright (published version):||2019 International Joint Conferences on Artificial Intelligence||Keywords:||Recommender Systems; eXplainable artificial intelligence (XAI); Contributions-based method; Multilayer perceptron (MLP)||DOI:||10.24963/ijcai.2019/376||Other versions:||https://www.ijcai.org/proceedings/2019/376||Language:||en||Status of Item:||Peer reviewed||Is part of:||Kraus, S. (ed.). Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence||Conference Details:||Twenty-Eighth International Joint Conferences on Artifical Intelligence (IJCAI), Macao, 10-16 August 2019|
|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.