HYBRID Course: Machine Learning A at University of Copenhagen in Sep-Oct 2024
The Department of Computer Science at the University of Copenhagen is offering a HYBRID course titled ‘Machine Learning A’ from Sep-Oct 2024. The course is a 7.5 ECTS master-level course that covers basic theory and algorithms of machine learning. The course is designed for students with a solid background in linear algebra, calculus, probability theory, and basic Python programming skills. It also assumes basic knowledge of LaTeX for typing home assignments.
The course covers topics such as the meaning of generalization beyond a finite sample under the independent identically distributed (i.i.d.) assumption, K-Nearest Neighbors algorithm, Perceptron, Linear Regression, Logistic Regression, Regularization and working in the feature space, Markov’s, Chebyshev’s, and Hoeffding’s inequalities, Generalization bounds for finite sets of prediction rules, Generalization bounds based on training/validation/test sets, Lower bound for generalization (the impossibility of generalization in the worst case), Occam’s Razor bound for countable sets of prediction rules and its application to Decision Trees, Random Forests, Neural Networks, Principal Component Analysis (PCA), Clustering: k-means & k-means++ algorithms, and Non-linear Dimensionality Reduction via Stochastic Neighbor Embedding.
The course will be delivered in a HYBRID format, allowing students to participate either physically or remotely via Zoom. The lectures will be recorded, and students will have a choice of physical and online exercise classes. The course is open to students from other universities and people from industry.
Registration for the course is open until 27 August 2024. Further information about the course can be found at https://kurser.ku.dk/course/ndak22000u/ and https://sites.google.com/diku.edu/machine-learning-courses/mla.
Registration links for Credit Students, EU Students, Non-EU Students, and Continuing Education Applicants can be found on the course website.