On Quantifying Literals in Boolean Logic and Its Applications to
Explainable AI

v1v2 (latest)

On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI

23 August 2021

ArXiv (abs)PDF HTML

Papers citing "On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI"

8 / 8 papers shown

Title
A New Class of Explanations for Classifiers with Non-Binary Features Chunxi Ji Adnan Darwiche FAtt 74 3 0 28 Apr 2023
On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits Alexis de Colnet Pierre Marquis 53 9 0 30 Jan 2023
Feature Necessity & Relevancy in ML Classifier Explanations Xuanxiang Huang Martin C. Cooper António Morgado Jordi Planes Sasha Rubin FAtt 69 19 0 27 Oct 2022
Logic-Based Explainability in Machine Learning Sasha Rubin LRM XAI 137 40 0 24 Oct 2022
Eliminating The Impossible, Whatever Remains Must Be True Jinqiang Yu Alexey Ignatiev Peter Stuckey Nina Narodytska Sasha Rubin 89 23 0 20 Jun 2022
On Tackling Explanation Redundancy in Decision Trees Yacine Izza Alexey Ignatiev Sasha Rubin FAtt 100 64 0 20 May 2022
On the Computation of Necessary and Sufficient Explanations Adnan Darwiche Chunxi Ji FAtt 62 19 0 20 Mar 2022
Tractable Boolean and Arithmetic Circuits Adnan Darwiche TPM 81 13 0 07 Feb 2022