About the Course

Deep learning based methods and their uses in various AI applications are very rapidly transforming science and technology. Although there is a tremendous interest in such methods in various fields such as computer vision, pattern recognition, speech recognition, natural language processing, robotics etc., the computational mechanisms for trust and responsibility in AI are still unsolved problems. This course provides an opportunity to students to raise awareness about the social, ethical and policy implications of AI; to study and develop deep learning based methods that are robust, explainable and fair.

This is a graduate-level course taught (CENG7880) at the Dept. of Computer Engineering, METU.

Catalog Description

Ethical concepts and principles of trust and responsibility in AI; computational methods for dependability and robustness in AI; computational methods for explainability in AI; computational methods for bias and fairness in AI.

Background Requirements

Instructor

Prof. Dr. Sinan Kalkan
METU Dept. of Computer Engineering and METU Robotics and AI Center
https://user.ceng.metu.edu.tr/~skalkan/

Syllabus

The syllabus for the course is available here.

Course Schedule

  • Mondays between 9:40-12:30 at BMB-5, starting on 28 September 5 October.

Announcements

  • Please attend the first lecture (5 October) to be considered for registration to the course.

Weekly Coverage

Week Topics Material
Week 1 (28 Sept) No lecture owing to the opening ceremony  
Week 2 (5 Oct ) Introduction to the course and the main concepts in trustworthy and responsible AI slides
Week 3 (12 Oct) Robustness to Label and Covariate Shifts slides
Week 4 (19 Oct) Robustness Evaluation Bounds, Adversarial Robustness slides
Week 5 (26 Oct) Robustness: Adversarial Defenses, Verifying Robustness. Uncertainty: Calibration, Conformal Prediction. slides