Introductory Master's Course to Machine Learning (ML), which is both a cornerstone of Artificial Intelligence (AI) and a top skill sought by IT employers. Today ML is everywhere: search engines use it to improve answers, email programs use it to filter spam, banks use it to predict stock markets, doctors use it to recognize tumors, robots use it to localize themselves and to understand their environment, video games use it to enhance the player's experience, smartphones use it to recognize objects / faces / gestures / voices / music, etc.
This course covers basic and advanced theory and methods of Machine Learning. From this wide field, we focus on neural networks, probabilistic models, and reinforcement learning in both theory and practice. Students will solve theoretical exercises and perform programming tasks; after just a few lectures, they will be able to implement a neural network which performs image classification better than any other known method. The intention of this course is to lay a solid groundwork for the student, such that he/she will be able to understand advanced state-of-the-art methods, to skillfully use diverse methods to solve practical problems, and to properly interpret results.
Requirements: Basic knowledge of calculus, linear algebra, and probability theory
Master's students will gain familiarity with state-of-the-art machine learning; focusing on neural networks, probabilistic modeling, and reinforcement learning. After successfully passing this course, students will have the knowledge to tackle state-of-the-art problems in both theory and practice.
The course includes lectures, TA sessions, and graded exercise sheets including programming assignments.
Written exam and graded exercise sheets, including programming assignments.
- Bishop, Christopher M.. Pattern Recognition and Machine Learning. Softcover reprint of the original 1st edition 2006 (corrected at 8th printing 2009). New York, NY: Springer New York, 2016.
- Goodfellow, Ian, Bengio, Yoshua, Courville, Aaron. Deep learning. Cambridge, Massachusetts London, England: The MIT Press, 2016.
- Hastie, Trevor J., Tibshirani, Robert, Friedman, Jerome. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. [corrected at 5th printing]. New York, N.Y.: Springer, 2011.
- Pattern Recognition and Machine Learning
- Supervised Sequence Labelling with Recurrent Neural Networks
- Sutton, Richard S., Barto, Andrew. Reinforcement learning: an introduction. Second edition. Cambridge, Massachusetts London, England: The MIT Press, 2018.
- Wasserman, Larry. All of statistics: a concise course in statistical inference. New York: Springer, 2010.
- Master of Science in Artificial Intelligence, Lecture, 1st year
- Master of Science in Computational Science, Lecture, Elective, 1st year
- Master of Science in Computational Science, Lecture, Elective, 2nd year
- Master of Science in Financial Technology and Computing, Lecture, 2nd year
- Master of Science in Informatics, Lecture, 1st year
- Master of Science in Informatics, Lecture, 2nd year
- Master of Science in Management and Informatics, Lecture, Elective, 2nd year
- PhD programme of the Faculty of Informatics, Lecture, Elective, 1st year (4 ECTS)