Explainable constraint solving and optimization
ID
MSCA-2020-BBogaerts01
Supervisors
Project description
As artificial intelligence (AI) tools employ more advanced reasoning mechanisms and computation, it becomes increasingly difficult to understand why certain decisions are made. Explainable AI research aims to fulfill the need for trustworthy AI systems that can explain their reasoning in a human-understandable way. I am mainly interested in explainable symbolic AI, in particular constraint solving and optimization (including answer set programming, satisfiability solving).
In a recent preliminary study, we started working on a framework for explainable constraint solving (ECAI 2020), but that study erected many more research questions related to scalability (the ability to explain large instances), generality (the ability to answer different types of questions) and interactability (the ability to interact in a natural and fluent way with a user).
In am interested in research in the general area as well as in related fields such as explainable planning. Possible topics include:
- Efficient algorithms for explanation generation (both for satisfiable and unsatisfiable problems), for instance building on existing (maximal) satisfiability solvers
- Researching conceptual questions as to what constitutes a “good” explanation in the context of constraint solving
- Researching notions of abstraction in the context of explanations
- Researching aspects of interactivity in the context of explaining constraint problems.
About the research Group
Artificial Intelligence Lab
The Artificial Intelligence Lab, founded in 1983 by Prof. Dr. Luc Steels, is the first AI lab on the European mainland. It is headed by Prof. Dr. Ann Nowé and Prof. Dr. Bernard Manderick. During its history of more than three decades, the VUB AI Lab has been following two main routes towards the understanding of intelligence: both the symbolic route (classical AI) as the dynamics route (complex systems science).
Since its foundation, more than 50 people have received a PhD degree at the Artificial Intelligence Lab, of which 18 in the past 5 years only. The total amount of publications sums up to more than 850 publications which are cited more than 24.000 times, 8500 times in the last 5 years. The lab also has experience in setting up of spin-offs (5 since its beginning). The research group is provided with standard hardware and software utilities and departmental services (secretary and ICT support). The COMO group of the AI-lab focuses on the one hand on the modeling of natural phenomena, and on the other hand on developing algorithms for complex problem solving inspired by these natural phenomena. The lab has experience in a wide range of learning techniques such as: Reinforcement Learning, Genetic Algorithms, Neural Networks, Support Vector Machines, Graphical models including Bayesian Networks, Genetic algorithms etc.