Deep Learning (MIT Press Book) by Yoshua Bengio, Ian Goodfellow, and Aaron Courville.
From the webpage:
Draft chapters available for feedback – August 2014
Please help us make this a great book! This draft is still full of typos and can be improved in many ways. Your suggestions are more than welcome. Do not hesitate to contact any of the authors directly by e-mail or Google+ messages: Yoshua, Ian, Aaron.
- Table of Contents
- Deep Learning for AI
- Linear Algebra
- Probability and Information Theory
- Numerical Computation
- Feedforward Deep Networks
- Structured Probabilistic Models: A Deep Learning Perspective
- Unsupervised and Transfer Learning
- Convolutional Networks
- Sequence Modeling: Recurrent and Recursive Nets
- Confronting the Partition Function
Teaching a subject isn’t the only way to learn it cold. Proofing a book on a subject is another way to learn material cold.
Ready to dig in?
I first saw this in a tweet by Gregory Piatetsky