Introduction to Logic-based Machine Learning

Over the last few decades, there has been a growing interest in Machine Learning. There are many different approaches to Machine Learning such as Artificial Neural Networks, Decision Trees and Reinforcement Learning, each with their own advantages and disadvantages.

The main advantage of Logic-based Machine Learning is that because the learned knowledge is expressed as a set of logical rules, it is compact and explainable. Explainable Artificial Intelligence is a topic of increasing importance – the recent General Data Protection Regulation (GDPR) requires actions taken as a result of a prediction from a learned model to be justified.

A seminar given by Mark Law introducing the ILASP systems.

This chapter introduces the basic concepts necessary to understand the rest of the manual.

  1. Logic and Logic Programming
  2. Answer Set Programming
  3. Inductive Logic Programming
  4. Learning Answer Set Programs from Examples