Abduction-based explanations for machine learning models
The growing range of applications of Machine Learning (ML) in a multitude of settings
motivates the ability of computing small explanations for predictions made. Small …
motivates the ability of computing small explanations for predictions made. Small …
Towards trustable explainable AI
A Ignatiev - … Joint Conference on Artificial Intelligence-Pacific …, 2020 - research.monash.edu
Explainable artificial intelligence (XAI) represents arguably one of the most crucial
challenges being faced by the area of AI these days. Although the majority of approaches to …
challenges being faced by the area of AI these days. Although the majority of approaches to …
Conflict-driven clause learning SAT solvers
One of the most important paradigm shifts in the use of SAT solvers for solving industrial
problems has been the introduction of clause learning. Clause learning entails adding a …
problems has been the introduction of clause learning. Clause learning entails adding a …
Logic-based explainability in machine learning
J Marques-Silva - … Knowledge: 18th International Summer School 2022 …, 2023 - Springer
The last decade witnessed an ever-increasing stream of successes in Machine Learning
(ML). These successes offer clear evidence that ML is bound to become pervasive in a wide …
(ML). These successes offer clear evidence that ML is bound to become pervasive in a wide …
SAT-based rigorous explanations for decision lists
A Ignatiev, J Marques-Silva - … and Applications of Satisfiability Testing–SAT …, 2021 - Springer
Decision lists (DLs) find a wide range of uses for classification problems in Machine
Learning (ML), being implemented in anumber of ML frameworks. DLs are often perceived …
Learning (ML), being implemented in anumber of ML frameworks. DLs are often perceived …
On validating, repairing and refining heuristic ML explanations
Recent years have witnessed a fast-growing interest in computing explanations for Machine
Learning (ML) models predictions. For non-interpretable ML models, the most commonly …
Learning (ML) models predictions. For non-interpretable ML models, the most commonly …
A survey on applications of quantified Boolean formulas
The decision problem of quantified Boolean formulas (QBFs) is the archetypical problem for
the complexity class PSPACE. Beside such theoretical aspects QBF also provides an …
the complexity class PSPACE. Beside such theoretical aspects QBF also provides an …
[PDF][PDF] Formally Explaining Neural Networks within Reactive Systems
Deep neural networks (DNNs) are increasingly being used as controllers in reactive
systems. However, DNNs are highly opaque, which renders it difficult to explain and justify …
systems. However, DNNs are highly opaque, which renders it difficult to explain and justify …
On symbolically encoding the behavior of random forests
Recent work has shown that the input-output behavior of some machine learning systems
can be captured symbolically using Boolean expressions or tractable Boolean circuits …
can be captured symbolically using Boolean expressions or tractable Boolean circuits …
From Single-Objective to Bi-Objective Maximum Satisfiability Solving
The declarative approach is key to efficiently finding optimal solutions to various types of NP-
hard real-world combinatorial optimization problems. Most work on practical declarative …
hard real-world combinatorial optimization problems. Most work on practical declarative …