Machine Learning

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.