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 02 | Welcome | |
| Mon Sep 07 | No Class (holiday) | |
| Deep Networks | ||
| Wed Sep 09 | Feed Forward Networks: Introduction | Written 1 Out |
| Mon Sep 14 | Feed Forward Networks: Learning | |
| Wed Sep 16 | Backpropagation | Written 1 Due |
| Mon Sep 21 | Automatic Differentiation | Written 2 Out |
| Wed Sep 23 | Optimization | |
| Supervised Learning | ||
| Mon Sep 28 | Convolutional Neural Networks | Written 2 Due |
| Wed Sep 30 | CNN Architectures | Written 3 Out |
| Mon Oct 05 | Interpretability | |
| Wed Oct 07 | How to Tame Your Deep Neural Network | |
| Mon Oct 12 | Modeling Sequences | Written 3 Due |
| Wed Oct 14 | Modeling Long-Term Dependencies | Programming 1 Out |
| Mon Oct 19 | Attention | |
| Wed Oct 21 | NLP and Transformers | |
| Mon Oct 26 | Graph Neural Networks - I | Programming 1 Due |
| Wed Oct 28 | Graph Neural Networks - II | Programming 2 Out |
| Mon Nov 02 | Supervised Learning Applications - I | |
| Wed Nov 04 | Supervised Learning Applications - II | |
| Unsupervised Learning | ||
| Mon Nov 09 | Generative Models: Introduction | Programming 2 Due |
| Wed Nov 11 | Autoregressive Models | Written 4 Out |
| Mon Nov 16 | No-class | |
| Wed Nov 18 | Normalizing Flows | Written 4 Due |
| Mon Nov 23 | Variational Autoencoders | |
| Wed Nov 25 | Generative Adversarial Networks | Programming 3 Out |
| Assorted Topics | ||
| Mon Nov 30 | Self-Supervised Learning | |
| Wed Dec 02 | Deep Reinforcement Learning - I | Programming 3 Due |
| Mon Dec 07 | Deep Reinforcement Learning - II | Programming 4 Out |
| Wed Dec 09 | Course Review | |
| Tue Dec 15 | Final Exam (12:45pm-2:45pm) | Programming 4 Due |