Current course offerings

Please Note: Course profiles marked as not available may still be in development.

Course description

Biological datasets often include large numbers of features (e.g., species, climatic variables, morphological attributes) that exhibit complex, nonlinear relationships with each other. The human brain, unassisted, is ill-equipped to deal with such information-rich datasets. When the number of features is especially large, or the relationships between them especially complex, even generalized linear models (QBIO7005), the tool-of-choice in scientific inference, may not be up to the job. In this course students will learn the essential theory behind the most commonly used unsupervised and supervised learning techniques in ecological and evolutionary research, and implement these techniques using R to find solutions to a range of real world biological problems. The first half of the course will focus on supervised learning (weeks 1-5), with an emphasis on classification and regression problems. The second half of the course (weeks 6-10) will focus on multivariate data and unsupervised learning, with an emphasis on clustering and dimension reduction. 

Archived offerings