Rebecca Morrison works at the interface between physics-based and data-driven models. In particular, she researches sparse structure learning in non-Gaussian graphical models and representations of model inadequacy in reduced systems. These topics are motivated by the goal to make reliable predictions of physical systems using computational models, physical constraints, and available data sets.
uncertainty quantification, applied probability, probabilistic graphical models, model inadequacy, Markov random fields, calibration and validation, predictive modeling
CSCI 2820 - Linear Algebra with Computer Science Applications
Introduces the fundamentals of linear algebra in the context of computer science applications. Includes vector spaces, matrices, linear systems, and eigenvalues. Includes the basics of floating point computation and numerical linear algebra.