120 credits including 90 credits in statistics, or 120 credits including 60 credits in statistics and 30 credits in mathematics and/or computer science. 7.5 credits programming in R, Python or Julia.
The course is a broad introduction to machine learning (ML) and covers supervised, unsupervised, and reinforcement learning. The course covers core ideas in ML, such as training, validation, and test of predictive models, cross-validation, (stochastic) gradient descent, ensembles, (convolutional, feed-forward, and transformer) neural networks, probabilistic mixtures, (variational) autoencoders, and bandits. The subjects are studied both theoretically, and practically in computer assignments and through an applied ML project.
