Machine Learning for Biomedical Data - GSND 5355Q

This class is a ‘hands on’ introduction to methods and tools for machine learning for biomedical research. Topics to be included will be model training and validation, regression and regularization, unsupervised learning and clustering, dimension reduction and smoothing, supervised learning and classification, neural networks, and Bayesian learning and inference. We will generally describe the history, theory, and methods for each approach, discuss appropriate situations for application, and practice and apply computer code for applying each method. The goal of this course is to establish a fundamental understanding and working knowledge of machine learning tools. This course is also distinct in its application on biomedical data– examples come from a variety of low and high dimensional research problems, such as epidemiology, clinical trails, biomarker discovery, and -omics data analysis. Students be expected to use R and GitHub throughout this course.  

Fall 2025 syllabus is available here.