CS 335: Fair, Accountable, and Transparent (FAccT) Deep LearningStanford University Spring 2020 Instructors Dr. Wei Wei | Office Hours: Friday 3:30-4:30 PM on Zoom Prof. James Landay | Office Hours: Wednesday 10:30-11:00 AM on Zoom Course Assistant Josh Payne | Office Hours: Friday 10:00-11:00 AM on AccessBell Enrollment PolicyInterested students must complete an enrollment survey. Enrollments will be approved by the instructors. Note: For students who have finished the survey before Feb 10, 2020, please submit the survey again so that we can have your email address. Course InfoDeep learning-based AI systems have demonstrated remarkable learning capabilities. A growing field in deep learning research focuses on improving the Fairness, Accountability, and Transparency (FAccT) of a model in addition to its performance. Although FAccT will be difficult to achieve, emerging technical approaches in this topic show promise in making better FAccT AI systems. In this course, we will study the rigorous computer science techniques necessary for FAccT deep learning and dive into the technical underpinnings of topics including fairness, robustness, interpretability, accountability, and privacy. These topics reflect state-of-the-art research in FAccT, are socially important, and they have strong industrial interest due to government and other policy regulation. This course will focus on the algorithmic and statistical methods needed to approach FAccT AI from a deep learning perspective. We will also discuss several application areas where we can apply these techniques. This course requires students to have intermediate mathematical and programming backgrounds in machine learning and deep learning. PrerequisitesThis course requires a graduate-level knowledge of statistics, machine learning, and AI. The student is expected to have taken any one of the following classes or their advanced equivalents: CS 230, CS 236, CS 273b, CS224n or CS231n. Alternatively, students who have taken CS 229 can be admitted with permission from the instructor. Enrollment will be limited to 30 students who will be chosen by application. Weekly Reading AssignmentsOur guidelines on required weekly reading assignments are available here. Course ProjectsStudents are expected to complete a project related to one of the topics covered in the class. Projects are expected to be computational in nature. However, alternative formats of projects can be permitted per instructors’ approval. Students should refer to the project guidelines. |