Memory- and neural-network-based expert system

By Chung K. Shin, Sang C. Park. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning (2019, background): “They tested a wide range of datasets and found that sensitivity and activity tended to do best for many datasets [Shin and Park, 1999; Shin et al., 2000; Im and Park, 2007].”
How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, methodology): “Shin and colleagues [46, 47, 51] paired MLPs with CBR operating over the same dataset, proposing that this hybrid system “can give example-based explanations together with prediction values of the neural network” [47, p.637].”
Hybrid case-based reasoning system by cost-sensitive neural network for classification (2016, methodology): “Sensitivity, activity saliency and relevance mechanisms are used in Shin and Park (1999), Shin et al. (2000), Im and Park (2007) and Park et al. (2004) to ﬁnd symbolic feature weights from back-propagation neural network (BPNN).”