Textbooks
The lectures do not map to any particular book or
set of books. Rather, they are
interactive and often follow student questions and class discussion. Nonetheless, the following two books
would be particularly useful:
·
Machine
Learning, by Tom Mitchell. This book is easy to read and has
many beautiful and intuitive explanations and examples, some of which we will
use in class. But it is quite dated, and covers only some 40% of the
topics we will discuss.
·
Machine Learning: A Probabilistic Perspective, by Kevin P. Murphy, 2012. A
much more recent and more comprehensive textbook, one of the better ones
around. A good reference book for Machine Learning. However, because it came out before the
recent Deep Learning craze, so it only devotes a short chapter to it.
·
Deep Learning, by Ian Goodfellow, Yoshua Bengio, Aaron Courville and
Francis Back, 2016.