Machine learning (ML) and logical reasoning have been the two key pillars of AI since its inception, and yet, there has been little interaction between these two sub-fields over the years. At the same time, each of them has been very influential in their own way. Despite this progress, there are new problems, as well as opportunities, on the horizon that seem solvable only via a combination of ML and logic. One such problem is the need for suitable logic-based testing, analysis, and verification (TAV) methods tailored to ML models. Another is the application of ML to SAT/SMT solvers, program analysis and other verification tools to make them more scalable. As a consequence, there is an urgent need for experts (theorists and practitioners) in these fields to work together in order to enable development of novel solutions to problems deemed impossible otherwise.
Our Goal
In order to explore the above topic of combinations of ML and Logic, we are organizing an online seminar where we plan to bring together speakers who are world-renowned practitioners and theorists in ML, verification, security, and logic in AI to speak on their pioneering research at the intersection of logical reasoning and ML.