Feature necessity and relevancy in machine learning explanations
From MaRDI portal
Cites work
- A logic for binary classifiers and their explanation
- A logic of ``black box classifier systems
- A SAT-based approach to learn explainable decision sets
- A structure-preserving clause form translation
- A theory of diagnosis from first principles
- A unified logical framework for explanations in classifier systems
- Assessing heuristic machine learning explanations with model counting
- Binary Decision Diagrams
- Blocked clause elimination for QBF
- Branching Programs and Binary Decision Diagrams
- Certified logic-based explainable AI -- the case of monotonic classifiers
- Computational Complexity
- Counterexample-guided abstraction refinement for symbolic model checking
- Decision tree induction based on efficient tree restructuring
- Decomposable negation normal form
- Deep learning
- DepQBF 6.0: a search-based QBF solver beyond traditional QCDCL
- Efficient Boolean manipulation with OBDD's can be extended to FBDD's
- Explaining black-box classifiers: properties and functions
- Explanation in artificial intelligence: insights from the social sciences
- Feature necessity \& relevancy in ML classifier explanations
- Graph-Based Algorithms for Boolean Function Manipulation
- Greedy function approximation: A gradient boosting machine.
- scientific article; zbMATH DE number 3902554 (Why is no real title available?)
- On quantifying literals in Boolean logic and its applications to explainable AI
- On Tackling Explanation Redundancy in Decision Trees
- On the (complete) reasons behind decisions
- On the reasons behind decisions
- On the Tractable Counting of Theory Models and its Application to Truth Maintenance and Belief Revision
- PySAT: a Python toolkit for prototyping with SAT oracles
- Random forests
- SAT-based rigorous explanations for decision lists
- Scikit-learn: machine learning in Python
- The complexity of logic-based abduction
- Towards formal XAI: formally approximate minimal explanations of neural networks
- Tractability of explaining classifier decisions
This page was built for publication: Feature necessity and relevancy in machine learning explanations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6834472)
