Date 
Topic covered 
Assignments 












23Aug 
Class syllabus 



Introduction to Artificial Intelligence (AI) 


Introduction to Machine Learning (ML) 


Introduction to Keras/TensorFlow 




30Aug 
Applied Mathematics 
(all) Deep Learning,
https://en.wikipedia.org/wiki/Deep_learning 


Introduction to Linear Algebra 
(all) Unstructured Data,
http://en.wikipedia.org/wiki/Unstructured_data 


Introduction to Probability 
(all) Deep Learning, Chapters 14 



(optional) Artificial Neural Networks,
https://en.wikipedia.org/wiki/Artificial_neural_network 



(optional) Keras docs, https://keras.io/ 





6Sep 
Information Theory & Machine Learning Fundamentals 
(all) Deep Learning, Chapters 45 


Introduction to Information Theory 


Introduction to Machine Learning (Part 1) 


Assignment 1 



13Sep 
Introduction to Machine Learning (Part 2) 
(all) Deep Learning, Chapter 56 


The Multilayer Perceptron & Feedforward Networks 
(optional) "Learning
Representations by BackPropagating Errors" (Nature),
https://www.nature.com/nature/journal/v323/n6088/abs/323533a0.html 


Architecture & GradientBased Learning 



BackPropagation of Errors 




20Sep 
Combatting Overparametrization: Regularization 
(all) Deep Learning, Chapter 7 


Prior Beliefs:
Statistical & Structural Forms 


Tricks: Ensembling & Adversarial Training 




27Sep 
Parameter Optimization 
(all) Deep Learning, Chapter 8 


Assignment 1 Due 


Assignment 2 




4Oct 
Team Presentations: Project Proposal 





11Oct 
Convolutional Networks 
(all) Deep Learning, Chapter 9 





18Oct 
Modeling Sequences: Recurrence and Recursion 
(all) Deep Learning, Chapter 10 


Special Topic: Neural Language Modeling 






25Oct 
Practical Methodology 
(all) Deep Learning, Chapter 11 


Assignment 2 Due 
(optional) Neural Networks: Tricks of the Trade,
2nd Edition  "Practical Recommendations for GradientBased Training of
Deep Architectures",
https://link.springer.com/chapter/10.1007/9783642352898_26 




1Nov 
Neural Network Applications 
(all) Deep Learning, Chapter 12 




8Nov 
Autoencoders 
(all) Deep Learning, Chapter 14 



(optional) Deep Learning, Chapter 13 (Linear Factor Models) 





15Nov 
Representation Learning 
(all) Deep Learning, Chapters 15 





22Nov 
Thanksgiving break, no classes 



29Nov 
Special Topic (TBA) 



Candidate Topic: (Deep) Generative Models & Approximate
Inference 
(optional) Deep Learning, Chapter 16, 19, & 20 


Candidate Topic: Deep Security: Adversarial Learning 



Candidate Topic: Memory Models & Rule Extraction 





6Dec 
Team Presentations 






13Dec 
Team Presentations 



































































































































