Fall 2018


Course Description

This course provides a comprehensive introduction to deep neural networks. Major topics include multilayer perceptrons, convolutional neural networks, recurrent neural networks, practical aspects of training deep neural networks and generative probabilistic modeling with deep neural networks. Students will learn basic concepts of deep learning as well as hands on experience to solve real-life problems. This course requires strong background in linear algebra, probability and statistics and machine learning. Python will be used for all the assignments.

Optional Textbook

Deep Learning Book

Deep Learning Frameworks

PyTorch (Preferred)

Tensorflow

Tentative Schedule

Date Lecture Misc
  Introduction  
Wed Aug 29 Welcome  
Mon Sep 03 No Class (holiday)  
Wed Sep 05 Machine Learning Review Homework 1 Out
Mon Sep 10 No Class (instructor out-of-office)  
Wed Sep 12 No Class (instructor out-of-office) Homework 1 Due
  Deep Networks  
Mon Sep 17 Feed Forward Networks: Introduction  
Wed Sep 19 Feed Forward Networks: Learning Homework 2 Out
Mon Sep 24 Backpropagation  
Wed Sep 26 Automatic Differentiation Homework 2 Due
Mon Oct 01 Optimization Homework 3 Out
  Supervised Learning  
Wed Oct 03 Convolutional Neural Networks  
Mon Oct 08 Alternative Convolutional Layers Homework 3 Due, Programming Assignment 1 Out
Wed Oct 10 Modeling Sequences with Neural Networks  
Mon Oct 15 Modeling Long-Term Dependencies  
Wed Oct 17 Practical Tricks for Training Programming Assignment 1 Due, Homework 4 Out
Mon Oct 22 No-class (instructor out-of-office)  
Wed Oct 24 No-class (instructor out-of-office) Homework 4 Due, Programming Assignment 2 Out
Mon Oct 29 Supervised Learning Applications - I  
Wed Oct 31 Supervised Learning Applications - II  
  Unsupervised Learning  
Mon Nov 05 Autoencoders Programming Assignment 2 Due
Wed Nov 07 Deep Generative Models - I Programming Assignment 3 Out
Mon Nov 12 Deep Generative Models - II  
Wed Nov 14 Deep Generative Models - III  
Mon Nov 19 Applications of Deep Generative Models Programming Assignment 3 Due
  Assorted Topics  
Wed Nov 21 Max-Margin Learning and Siamese Networks Programming Assignment 4 Out
Mon Nov 26 Deep Reinforcement Learning - I  
Wed Nov 28 Deep Reinforcement Learning - II Homework 5 Out
Mon Dec 03 Playing Go with Deep Neural Networks  
Wed Dec 05 Course Review Programming Assignment 4 Due
Tue Dec 11 Final Exam (12:45pm-2:45pm)