Deep learning. (English) Zbl 1373.68009

Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron

Adaptive Computation and Machine Learning. Cambridge, MA: MIT Press (ISBN 978-0-262-03561-3/hbk; 978-0-262-33743-4/ebook). xxii, 775 p. (2016).

The book presents solutions to intuitive problems, that is, problems that people solve intuitively, and that feel automatic, but are hard to be described. Deep learning solves the central problem in representation learning by introducing representations based on simpler ones. The text offers the mathematical and machine learning background needed to understand the concepts and techniques related to deep learning. The book is useful for undergraduate and graduate university students studying machine learning, and for software engineers working in domains requiring statistics and machine learning.

Reviewer: Florin Gorunescu (Craiova)

MSC:

68-02	Research exposition (monographs, survey articles) pertaining to computer science
62-02	Research exposition (monographs, survey articles) pertaining to statistics
62H25	Factor analysis and principal components; correspondence analysis
68T05	Learning and adaptive systems in artificial intelligence

Keywords:

machine learning; probability; information theory; numerical computation; deep networks; regularization; optimization; convolutional networks; sequence modeling; recurrent nets; recursive nets; linear factor models; autoencoders; representation learning; Monte Carlo methods; partition function; approximate inference; deep generative models