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 Frameworks
Communication
All written communication should be directed though Google Classroom. You can post publicly or privately depending on your preference. Emails won’t be responded to.
Schedule
| Date | Lecture | Misc |
|---|---|---|
| Introduction | ||
| Wed Aug 28 | Welcome | |
| Mon Sep 02 | No Class (holiday) | |
| Wed Sep 04 | Machine Learning Review | Written 1 Out |
| Deep Networks | ||
| Mon Sep 9 | Feed Forward Networks: Introduction | |
| Wed Sep 11 | Feed Forward Networks: Learning | Written 1 Due |
| Mon Sep 16 | Backpropagation | Written 2 Out |
| Wed Sep 18 | Automatic Differentiation | |
| Mon Sep 23 | Optimization | Written 2 Due |
| Supervised Learning | ||
| Wed Sep 25 | Convolutional Neural Networks | Written 3 Out |
| Mon Sep 30 | Alternative Convolutional Layers | |
| Wed Oct 02 | Modeling Sequences with Neural Networks | |
| Mon Oct 07 | Modeling Long-Term Dependencies | Written 3 Due |
| Wed Oct 09 | Practical Tricks for Training | Programming 1 Out |
| Mon Oct 14 | Supervised Learning Applications - I | |
| Wed Oct 16 | Supervised Learning Applications - II | |
| Unsupervised Learning | ||
| Mon Oct 21 | Deep Generative Models - I | Programming 1 Due |
| Wed Oct 23 | Deep Generative Models - II | Programming 2 Out |
| Mon Oct 28 | No-class (instructor out-of-office) | |
| Wed Oct 30 | No-class (instructor out-of-office) | |
| Mon Nov 04 | Deep Generative Models - III | Programming 2 Due |
| Wed Nov 06 | Deep Generative Models - IV | Written 4 Out |
| Mon Nov 11 | No-class (instructor out-of-office) | |
| Wed Nov 13 | No-class (instructor out-of-office) | Written 4 Due |
| Mon Nov 18 | Catch Up (VAE) | Programming 3 Out |
| Assorted Topics | ||
| Wed Nov 20 | Catch Up (GAN) | |
| Mon Nov 25 | Catch Up (Flow Models) | |
| Wed Nov 27 | Deep Reinforcement Learning - I | Programming 3 Due, Programming 4 Out |
| Mon Dec 02 | Deep Reinforcement Learning - II | |
| Wed Dec 04 | Course Review | |
| Tue Dec 10 | Final Exam (12:45pm-2:45pm) | Programming 4 Due |