Rule Extraction from Support Vector Machines: A Sequential Covering Approach

111 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.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “This is the approach of [93] , which proposes a method that extracts rules directly from the support vectors of a trained SVM us-ing a modiﬁed sequential covering algorithm.”
Rule extraction from support vector machines: A review (2010, methodology): “Abstract representation of SQRex-SVM [34].”
Explaining prediction models and individual predictions with feature contributions (2014, unknown): “Complex models, such as artificial neural networks [14, 15, 16, 17, 18] and SVM (Support Vector Machines) [19, 20, 10, 21, 22, 23, 24, 25] received most attention, because they are often very successful but non-transparent.”
Supervised classification and mathematical optimization (2013, methodology): “Other rule extraction techniques have been proposed in [16, 79, 169, 184].”
Human-in-the-loop machine learning: a state of the art (2022, methodology): “For SVMs, post-hoc explainability techniques applied are explanation by simplification, local explanations, visualizations and explanations by example (Barakat and Bradley 2007; Chen et al. 2007; Gaonkar et al. 2015).”
A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “Rule-based models: Decision rules have the structure of IF condition THEN label ELSE other label.”