Machine Learning in Public Health

Catalog description

This course provides students with a strong foundation in machine learning relevant to public health and biomedical applications. Topics include the data generating process, model selection and evaluation, generalized linear models, common supervised and unsupervised machine learning algorithms such as support vector machines, decision trees, random forests, neural networks, and k-means, and ethics and communication. Students will learn methods for optimal and proper implementation of machine learning, such as assessment of assumptions about the data generating process, feature generation, treatment of missing data, and reduction of bias. Students will gain familiarity with the potential power of machine learning in public health, as well as its particular challenges inherent to public health applications.