Teaching

Courses

• CS 7180 Actionable Interpretability
  Spring 2026
  Graduate seminar on modern interpretability research, with an emphasis on making methods "actionable", i.e., practically useful.
• DS 4440 Practical Neural Networks
  Multiple offerings
  Covers modern deep learning theory and practice, including recurrent, convolutional, and transformer architectures (up to modern Large Language Models).
• DS 2000 Programming with Data
  Multiple offerings
  Introduction to programming and data science in Python. Covers data manipulation, visualization, and basic statistical reasoning through hands-on homeworks.
• DS 4420 Machine Learning 2
  Multiple offerings
  Probabilistic machine learning including Bayesian methods, graphical models, approximate inference, and unsupervised learning techniques.
• CS 4100 Artificial Intelligence
  Spring 2017
  Undergraduate survey of AI covering search, constraint satisfaction, knowledge representation, planning, and an introduction to machine learning.
• CS 2500 Fundamentals of Computer Science 1
  Fall 2017
  Introduction to functional programming and program design. Covers recursion, higher-order functions, and systematic program construction.
• 150AIH AI in Health Informatics
  Tufts University · co-taught with Kevin Small
  Graduate course on artificial intelligence methods applied to health informatics, covering NLP, clinical text mining, and evidence-based medicine.