263-2400-00L Reliable and Interpretable Artificial Intelligence
| Semester | Autumn Semester 2019 |
| Lecturers | M. Vechev |
| Periodicity | yearly recurring course |
| Language of instruction | English |
Courses
| Number | Title | Hours | Lecturers | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 263-2400-00 V | Reliable and Interpretable Artificial Intelligence | 2 hrs |
| M. Vechev | ||||||
| 263-2400-00 U | Reliable and Interpretable Artificial Intelligence No exercise session in the first semester week. Exercise session will start in the second week of the semester. | 1 hrs |
| M. Vechev | ||||||
| 263-2400-00 A | Reliable and Interpretable Artificial Intelligence | 1 hrs | M. Vechev |
Catalogue data
| Abstract | 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. |
| Learning objective | 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. |
| Content | The course covers some of the latest research (over the last 2-3 years) underlying the creation of safe, trustworthy, and reliable AI (more information here: https://www.sri.inf.ethz.ch/teaching/riai2019): * 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 |
| Prerequisites / Notice | While not a formal requirement, the course assumes familiarity with basics of machine learning (especially probability theory, linear algebra, gradient descent, and neural networks). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH). For solving assignments, some programming experience in Python is excepted. |
Performance assessment
| Performance assessment information (valid until the course unit is held again) | |
Performance assessment as a semester course | |
| ECTS credits | 5 credits |
| Examiners | M. Vechev |
| Type | session examination |
| Language of examination | English |
| Repetition | The performance assessment is only offered in the session after the course unit. Repetition only possible after re-enrolling. |
| Mode of examination | written 90 minutes |
| Additional information on mode of examination | 30% of your grade is determined by mandatory project work and 70% is determined by a written exam. |
| Written aids | None |
| This information can be updated until the beginning of the semester; information on the examination timetable is binding. | |
Learning materials
| Main link | Information |
| Only public learning materials are listed. | |
Groups
| No information on groups available. |
Restrictions
| There are no additional restrictions for the registration. |
