Litcius/Paper detail

Explaining Deep Learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in XAI

Eoin M. Kenny, Mark T. Keane

2021Knowledge-Based Systems46 citationsDOIOpen Access PDF

Abstract

In this paper, the twin-systems approach is reviewed, implemented, and competitively tested as a post-hoc explanation-by-example solution to the eXplainable Artificial Intelligence (XAI) problem. In twin-systems, an opaque artificial neural network (ANN) is explained by “twinning” it with a more interpretable case-based reasoning (CBR) system, by mapping the feature weights from the former to the latter. Extensive comparative tests are performed, over four experiments, to determine the optimal feature-weighting method for such twin-systems. Twin-systems for traditional multilayer perceptron (MLP) networks (MLP–CBR twins), convolutional neural networks (CNNs; CNN–CBR twins), and transformers for NLP (BERT–CBR twins) are examined. In addition, Feature Activation Maps (FAMs) are explored to enhance explainability by providing an additional layer of explanatory insight. The wider implications of this research on XAI is discussed, and a code library is provided to ease replicability.

Topics & Concepts

WeightingComputer scienceArtificial intelligenceFeature (linguistics)Artificial neural networkConvolutional neural networkPerceptronMachine learningData miningPattern recognition (psychology)MedicinePhilosophyRadiologyLinguisticsExplainable Artificial Intelligence (XAI)Advanced Neural Network ApplicationsMachine Learning in Healthcare
Explaining Deep Learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in XAI | Litcius