Book - Deep Learning - MIT PRESS - Book Online 2019
Book - Deep Learning - MIT PRESS - Book Online 2019
To write your own document using our LaTeX style, math notation, or to copy
our notation page, download our templatefiles.
Deep Learning
• Table of Contents
• Acknowledgements
• Notation
• 1 Introduction
• Part I: Applied Math and Machine Learning Basics
o 2 Linear Algebra
o 3 Probability and Information Theory
o 4 Numerical Computation
o 5 Machine Learning Basics
• Part II: Modern Practical Deep Networks
o 6 Deep Feedforward Networks
o 7 Regularization for Deep Learning
o 8 Optimization for Training Deep Models
o 9 Convolutional Networks
o 10 Sequence Modeling: Recurrent and Recursive Nets
o 11 Practical Methodology
o 12 Applications
• Part III: Deep Learning Research
o 13 Linear Factor Models
o 14 Autoencoders
o 15 Representation Learning
o 16 Structured Probabilistic Models for Deep Learning
o 17 Monte Carlo Methods
o 18 Confronting the Partition Function
o 19 Approximate Inference
o 20 Deep Generative Models
• Bibliography
• Index
FAQ
• Can I get a PDF of this book?
No, our contract with MIT Press forbids distribution of too easily copied
electronic formats of the book.
• Why are you using HTML format for the web version of the book?
This format is a sort of weak DRM required by our contract with MIT
Press. It's intended to discourage unauthorized copying/editing of the
book.
Printing seems to work best printing directly from the browser, using
Chrome. Other browsers do not work as well.
If you notice any typos (besides the known issues listed below) or have
suggestions for exercises to add to the website, do not hesitate to contact the
authors directly by e-mail at: [email protected]
Since the book is complete and in print, we do not make large changes, only
small corrections.
Known issues: In outdated versions of the Edge browser, the "does not equal"
sign sometimes appears as the "equals" sign. This may be resolved by updating to
the latest version.