Accuracy vs. comprehensibility in data mining models

By Ulf Johansson, Lars Niklasson, Rikard König. 2004

51 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “Although it was not originally intended for extracting rules from opaque models, the generic proposition of G-REX has been extended to also account for model explainability purposes [190,211] .”
Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “Classification rules have been widely used to explain neural networks [2, 3, 21] but also to understand the global behavior of SVMs [15, 27].”
A Survey of Methods for Explaining Black Box Models (2018, methodology): “ covered by the set of rules, then a conjunctive (or m-of-n) rule is formed from fx;y^gconsidering all the possible antecedents. The procedure ends when all the target classes have been processed. In [40] Johansson et al. exploit G-REX [37], an algorithm for rule extraction, as function fto explain ”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “Similarly, Genetic Rule EXtraction (G-REX) [166, 167] employed genetic algorithms to generate IF-THEN rules with AND/OR operators.”
Principles and Practice of Explainable Machine Learning (2020, background): “ations. G-REX [47] is an approach ﬁrst introduced in genetic programming, in order to extract rules from data, but later works have expanding its score, rendering capable of addressing explainability [40, 39]. Another approach is introduced in [76], where the authors explore a way to learn rules in ”