Machine Learning A
In Fall 2024, Machine Learning A (MLA) will be taught by Christian Igel, Yevgeny Seldin, and Sadegh Talebi. The course covers theoretical and practical foundations of machine learning. The course assumes knowledge of linear algebra, calculus, probability theory, and basic programming skills. Please, check the following self-assessment assignment to test whether you have the necessary qualifications for the course. If you have difficulties solving it, check our preparing yourself for the course page.
We plan to cover the following topics:
Basics of probability theory and the meaning of generalization beyond a sample under the i.i.d. assumption
K-Nearest Neighbors algorithm
Perceptron
Linear Regression
Logistic Regression
Regularization and working in the feature space
Markov's and Hoeffding's inequalities and their application to derivation of generalization bounds
Generalization bounds based on training/validation/test sets
Lower bound for generalization (the impossibility of generalization in the worst case)
Occam's Razor bound and its application to Decision Trees
Random Forests
Neural Networks
Principal Component Analysis (PCA)
K-means clustering
Non-linear Dimensionality Reduction via Stochastic Neighbor Embedding
Practicalities
Programming Language: The working language of the course is Python. See the programming exercise in the self-assessment assignment to verify whether you are ready.
Course dates: The next round of the course will run from the 2th of September 2024 till the 3rd of November 2024 with a take-home written exam taking place in the last week of the course. We usually offer short workshops in the week prior to the course start to boost the students' background on math and programming prerequisites.
Lectures: The lectures will take place on Mondays 9:15-12:00 and Fridays 9:15-12:00. The lectures will be held at University of Copenhagen (North Campus), but they will be streamed via Zoom and video recordings will be uploaded to the internal course page. This means that it is possible to take the course fully remotely.
TA classes: We expect to have about 12 TA groups/classes and we allow our students to join any TA class they like and if they need they can attend more than one TA session. The TA sessions will be 3 hours long and will focus on going through solutions of assignments that have been submitted as well as help with ongoing course material. The TA sessions will be spread throughout the week, so it should not be a problem to find one that fits your schedule. Exact details about the time of TA classes will be provided later. We guarantee TA classes on Tuesdays (afternoon) and Fridays (afternoon), but there will be some other available time slots. To support remote participation, we will have one TA session over Zoom. TA sessions will not be recorded.
Home assignments: There will be weekly home assignments including theoretical and practical questions. We expect to have 6-7 assignments in total.
Final exam: The final exam is a 5-day take-home written exam, but it is designed in a way that it should be solvable within 2.5 days -- assuming you have followed the material throughout the course --, see the dates above. We provide 5 days to accommodate for potential overlap with exams in other courses and other commitments you might have (e.g., part-time job). The final exam includes theoretical and practical questions and must be solved individually.
Registration
The course welcomes applications from students enrolled at other universities as well as people from the industry. But it is also open to anyone interested in foundations of machine learning. All elements of the course (including the final assessment) can be followed fully remotely, hence the course can in principle be taken by anyone.
Relevant registration links:
Credit Students (for those enrolled at another Danish educational institute)
EU Students (for those enrolled at a non-Danish EU educational institute)
Non-EU Students (for those enrolled at an educational institute outside EU)
Continuing Education Applicants (for applicants from the industry or individuals not enrolled at an educational institute, etc.)
Contact
In case of questions, please contact the course responsible, Sadegh Talebi (m.shahi@di.ku.dk / mstalebi.edu@gmail.com).