Teaching

Guest Lecturer – Topics in AI: Explainability and Interpretability, Xin Tang, University of British Columbia

• Developed materials from scratch for two guest lectures, with one covering interpretable AI broadly and one covering modern interpretable computer vision
• Delivered lectures to a seminar of 10-20 graduate students

Guest Lecturer – Theory and Algorithms for Machine Learning, Cynthia Rudin, Duke University

• Modified materials for a lecture introducing neural networks
• Delivered lecture to a large class of ~100 graduate and undergraduate students

Guest Lecturer – Introduction to Machine Learning, Alina Jade Barnett, University of Rhode Island

• Developed materials about modern variable importance methods
• Delivered lecture a to ~30 undergraduate students

Teaching Assistant – Theory and Algorithms for Machine Learning (Graduate), Cynthia Rudin, Duke University

• Held recitations for groups of 20-30 students
• Developed homework problems
• Conducted office hours for large groups of students

Teaching Assistant – Introduction to Computer Vision (Graduate), Carlo Tomassi, Duke University

• Debugged homework and exams
• Held office hours

Student Mentor– Data Science Competition (Undergraduate), Cynthia Rudin, Duke University

• Guided original student-led research projects for five groups of undergraduate students, with several producing published papers

Student Mentor– MBS Externship (Graduate), Linda Ness, Rutgers University

• Consulted with a small group of masters students to help develop an original research project