Course Description
This course provides a comprehensive introduction to deep neural networks. Major topics include multilayer perceptrons, convolutional neural networks, sequence modeling with recurrent neural networks and transformers, 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 Piazza. You can post publicly or privately depending on your preference. Emails won’t be responded to.
Project
Details on course project can be found here.
Schedule and Syllabus
| Date | Lecture | Misc |
|---|---|---|
| Introduction | ||
| Wed Aug 31 | Welcome | |
| Mon Sep 05 | No Class (holiday) | |
| Deep Networks | ||
| Wed Sep 07 | Feed Forward Networks: Introduction | Written 1 Out |
| Mon Sep 12 | Feed Forward Networks: Learning | |
| Wed Sep 14 | Backpropagation | |
| Mon Sep 19 | Reverse Mode Automatic Differentiation | Programming 1 Out |
| Wed Sep 21 | Optimization | |
| Supervised Learning | ||
| Mon Sep 26 | Convolutional Neural Networks | Written 1 Due |
| Wed Sep 28 | CNN Architectures | |
| Mon Oct 03 | Interpretability | |
| Wed Oct 05 | Modeling Sequences | Programming 1 Due |
| Mon Oct 10 | No Class (instructor out of town) | |
| Wed Oct 12 | Mid-Term Exam (in class) | |
| Mon Oct 17 | Attention | |
| Wed Oct 19 | Transformers | |
| Mon Oct 24 | No Class (Fall Break) | |
| Wed Oct 26 | How to Tame Your Deep Neural Network | |
| Mon Oct 31 | Graph Neural Networks - I | |
| Wed Nov 02 | Graph Neural Networks - II | |
| Mon Nov 07 | Supervised Learning Applications | |
| Unsupervised Learning | ||
| Wed Nov 09 | Generative Models: Introduction | |
| Mon Nov 14 | Autoregressive Models | |
| Wed Nov 16 | Diffusion Models | |
| Assorted Topics | ||
| Mon Nov 21 | Self-Supervised Learning | |
| Wed Nov 23 | Fairness in AI | |
| Mon Nov 28 | Privacy and Security | |
| Wed Nov 30 | Course Review | |
| Mon Dec 05 | Project Presentations - I | |
| Wed Dec 07 | Project Presentations - II |