We have been curious in teaching computers to learn ever since they were first developed. The implications would be enormous if we knew how to teach them, via programming, to learn and improve automatically with use. Think of personal software assistants that learn their users’ changing interests and then highlight the stories from the online morning newspaper that are most relevant to them based on that information; computers that learn from medical records which treatments are best for new diseases; homes that learn to optimise energy costs based on the unique usage patterns of their occupants. If we could figure out how to teach machines, it would pave the way for all sorts of advanced computing applications and individualised experiences. Human learning skills (and shortcomings) may be better understood with a deeper knowledge of information processing methods for machine learning. Within the recent decade, “machine learning” and “artificial intelligence” have been widely used in a variety of settings. Both phrases are widely used in the scientific and media communities, often with overlapping but not always synonymous meanings. The authors of this book set out to define the terminologies at play here and, more specifically, to outline the role that machine learning plays in AI. The authors provide a literature analysis and a conceptual framework that explain how machine learning contributes to the development of (artificial) intelligent agents.