scholarly journals Adapting Numerical Representations of Lung Contours Using Case-Based Reasoning and Artificial Neural Networks

2012 ◽  
pp. 137-151 ◽  
Author(s):  
Julien Henriet ◽  
Pierre-Emmanuel Leni ◽  
Rémy Laurent ◽  
Ana Roxin ◽  
Brigitte Chebel-Morello ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Case Based Reasoning ◽  
Artificial Neural ◽  
Numerical Representations ◽  
Case Based

scholarly journals Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI

2019 ◽  
Author(s):  
Eoin M. Kenny ◽  
Mark T. Keane
Keyword(s):  
Neural Networks ◽  
Evaluation Method ◽  
Nearest Neighbor ◽  
Image Data ◽  
Black Box ◽  
Feature Weighting ◽  
Case Based Reasoning ◽  
Artificial Neural ◽  
Weighting Methods ◽  
Case Based

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.

Sign in / Sign up

Export Citation Format

Share Document