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 Sep 01 | Welcome | |
| Mon Sep 06 | No Class (holiday) | |
| Deep Networks | ||
| Wed Sep 08 | Feed Forward Networks: Introduction | Written 1 Out |
| Mon Sep 13 | Feed Forward Networks: Learning | |
| Wed Sep 15 | Backpropagation | |
| Mon Sep 20 | Automatic Differentiation | Written 1 Due, Programming 1 Out |
| Wed Sep 22 | Optimization | |
| Supervised Learning | ||
| Mon Sep 27 | Convolutional Neural Networks | |
| Wed Sep 29 | CNN Architectures | Programming 1 Due, Written 2 Out |
| Wed Oct 04 | Interpretability | |
| Wed Oct 06 | How to Tame Your Deep Neural Network | |
| Mon Oct 11 | Modeling Sequences | Written 2 Due, Programming 2 Out |
| Wed Oct 13 | Modeling Long-Term Dependencies | |
| Mon Oct 18 | Attention | |
| Wed Oct 20 | NLP and Transformers | |
| Mon Oct 25 | No Class (Fall Break) | Programming 3 Out |
| Wed Oct 27 | Graph Neural Networks - I | Programming 2 Due |
| Mon Nov 01 | Graph Neural Networks - II | |
| Wed Nov 03 | Supervised Learning Applications - I | |
| Mon Nov 08 | Supervised Learning Applications - II | Programming 3 Due, Written 3 Out |
| Unsupervised Learning | ||
| Wed Nov 10 | Generative Models: Introduction | |
| Mon Nov 15 | Autoregressive Models | |
| Wed Nov 17 | Normalizing Flows | Written 3 Due, Written 4 Out |
| Mon Nov 22 | Variational Autoencoders | |
| Wed Nov 24 | Generative Adversarial Networks | |
| Assorted Topics | ||
| Mon Nov 29 | Self-Supervised Learning | Written 4 Due, Programming 4 Out |
| Wed Dec 01 | Deep Reinforcement Learning - I | |
| Mon Dec 06 | Deep Reinforcement Learning - II | |
| Wed Dec 08 | Course Review | |
| Tue Dec 14 | Final Exam (12:45pm-2:45pm) | Programming 4 Due |