Statistical learning — that is, learning from data — and, in particular, probabilistic
model learning have become increasingly important in recent years.
Advances in information technology have facilitated an explosion of available
data. This explosion has been accompanied by theoretical advances, permitting
new and exciting applications of statistical learning methods to bioinformatics,
finance, marketing, text categorization, and other fields.
A welter of seemingly diverse techniques and methods, adopted from different
fields such as statistics, information theory, and neural networks, have
been proposed to handle statistical learning problems. These techniques are
reviewed in a number of textbooks (see, for example, Mitchell (1997), Vapnik
(1999), Witten and Frank (2005), Bishop (2007), Cherkassky and Mulier
(2007), and Hastie et al. (2009)).