1. Applied Math and Machine Learning Basics[P29-P165)
   1. Linear Algebra [31-53)
   2. Probability and Information Theory [53-80)
   3. Numerical Computation [80-98)
   4. Machine Learning Basics [98-165)
2. Deep Networks: Modern Practices [165-488)
   1. Deep Feedforward Networks [165-228)
   2. Regularization for Deep Learning [228-274)
   3. Optimization for Training Deep Models [274-330)
   4. Convolutional Networks [330-373)
   5. Sequence Modeling: Recurrent and Recursive Nets [373-423)
   6. Practical Methodology [423-445)
   7. Applications [445-488)
3. Deep Learning Research [488-721)
   1. Linear Factor Models [491-504)
   2. Autoencoders [504-528)
   3. Representation Learning [528-560)
   4. Structured Probabilistic Models for Deep Learning [560-592)
   5. Monte Carlo Methods [592-607)
   6. Confronting the Partition Function [607- 633)
   7. Approximate Inference [633-656)
   8. Deep Generative Models [656-723)