Overview
Creating reliable and explainable probabilistic models is a fundamental challenge to solving the artificial intelligence problem. This course covers some of the latest and most exciting advances that bring us closer to constructing such models. The main objective of this course is to expose students to the latest and most exciting research in the area of explainable and interpretable artificial intelligence, a topic of fundamental and increasing importance. Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of problems. To facilitate deeper understanding, an important part of the course will be a group hands-on programming project where students will build a system based on the learned material.
The course covers some of the latest research (over the last 2-3 years) underlying the creation of safe, trustworthy, and reliable AI:
- Adversarial Attacks on Deep Learning (noise-based, geometry attacks, sound attacks, physical attacks, autonomous driving, out-of-distribution)
- Defenses against attacks
- Combining gradient-based optimization with logic for encoding background knowledge
- Complete Certification of deep neural networks via automated reasoning (e.g., via numerical abstractions, mixed-integer solvers)
- Probabilistic certification of deep neural networks
- Training deep neural networks to be provably robust via automated reasoning
- Understanding and Interpreting Deep Networks
- Probabilistic Programming
Course project
The description of the course project can be found here. Code template, trained networks and sample test cases are uploaded here.Lectures
| No. | Date | Content | Slides | Exercises | Solutions |
|---|---|---|---|---|---|
| 1 | Sept 18 | Introduction |  |
|
|
| 2 | Sept 25 | Adversarial attacks I | |
|
|
| 3 | Oct 2 | Adversarial attacks II | |
|
|
| 4 | Oct 9 | Adversarial defenses + Certification | |
|
|
| 5 | Oct 16 | Box and MILP certification | |
|
|
| 6 | Oct 23 | Zonotope approximation | |
|
|
| 7 | Nov 6 | DeepPoly + Geometric Robustness | |
|
|
| 8 | Nov 13 | Visualizing CNNs | |
|
|
| 9 | Nov 20 | Querying and Training Deep Learning with Logic | |
|
|
| 10 | Nov 27 | Provable Defenses + Beyond the Single Neuron Convex Relaxations |
|
|
|
| 11 | Dec 4 | Randomized Smoothing |
|
|
|
| 12 | Dec 11 | Differential Privacy |
|
|
|
| 13 | Dec 18 | Final lecture: exam overview and open problem |
|