A tour of machine learning: An AI perspective

Issue title: ECAI 2012 Turing and Anniversary Track

Article type: Research Article

Authors: Sebag, Michele

Affiliations: TAO, CNRS–INRIA–LRI, Université Paris-Sud, 91405 Orsay Cedex, France. E-mail: sebag@lri.fr

Abstract: Machine Learning has been at the core of Artificial Intelligence since its inception. Many promises have been held, if one is to consider that Google is a living demonstration of AI. This paper presents a historical perspective on Machine Learning, describing how the emphasis was gradually shifted from logical to statistical induction, from induction to optimization, from the search of hypotheses to the search of representations. The paper concludes with a discussion about the new frontier of Machine Learning.

Keywords: Machine Learning, statistical learning, unsupervised learning, change of representation, reinforcement learning, machine reasoning

DOI: 10.3233/AIC-130580

Journal: AI Communications, vol. 27, no. 1, pp. 11-23, 2014