CLEAR combines counterfactual searches with local regression to produce explanations of any classifier, and measures their fidelity against the classifier's decision boundary.
Tickle, ‘Survey and critique of techniques for extracting rules from trained artifi- cial neural networks’,Knowledge-Based Systems, 8(6), 373–389, (December 1995)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Measurable Counterfactual Local Explanations for Any Classifier
CLEAR combines counterfactual searches with local regression to produce explanations of any classifier, and measures their fidelity against the classifier's decision boundary.