Symbolic Logic meets Machine Learning: A Brief Survey in Infinite Domains

Abstract

The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence (AI). The deduction camp concerns itself with questions about the expressiveness of formal languages for capturing knowledge about the world, together with proof systems for reasoning from such knowledge bases. The learning camp attempts to generalize from examples about partial descriptions about the world. In AI, historically, these camps have loosely divided the development of the field, but advances in cross-over areas such as statistical relational learning, neuro-symbolic systems, and high-level control have illustrated that the dichotomy is not very constructive, and perhaps even ill-formed. In this article, we survey work that provides further evidence for the connections between logic and learning. Our narrative is structured in terms of three strands: logic versus learning, machine learning for logic, and logic for machine learning, but naturally, there is considerable overlap. We place an emphasis on the following "sore" point: there is a common misconception that logic is for discrete properties, whereas probability theory and machine learning, more generally, is for continuous properties. We report on results that challenge this view on the limitations of logic, and expose the role that logic can play for learning in infinite domains.

Logic Guided Genetic Algorithms

“…These ATs are typically simple domain-specific properties of the unknown function f that SR users are likely to know and can significantly enable SR methods to be more data efficient. Further, in recent years, we have seen an increasing effort by researchers to bring together the two pillars of AI, namely, machine learning (ML) and mathematical logic, with the aim of solving problems that neither approach by itself can feasibly solve (Belle 2020).…”