Advanced Machine Learning Applications in Biomedicine

4 units · Graduate courses (200-299)

Lecture, four hours; discussion, two hours. Requisite: course 200 or equivalent. Statistical models for analysis of biomedical data that captures the structure of the data and accounts for the constraints. Topics include Bayesian models, probabilistic graphical models, deep learning, time series, dynamical systems, stochastic processes, scalable inference (gradient descent, stochastic gradient descent, expectation-maximization, Markov chain Monte Carlo, variational inference), privacy-preserving inference (differential privacy, inference over encrypted data), interpretable machine learning, and fairness and bias. Letter grading.