Machine Learning

Machine Learning

In this course we will introduce the foundations of machine learning (ML). In particular, we will focus on understanding the theoretical aspects of ML that have made ML successful in a wide range of applications such as bioinformatics, computer vision, information retrieval, computer linguistics, robotics, etc.

The course gives a broad introduction into machine learning methods. After the lecture the students should be able to solve and analyze learning problems. The lecture is based on the previous machine learning courses offered by  Matthias Hein and Peter Ochs.

The tentative list of topics cover:

• Probability theory
• Maximum Likelihood/Maximum A Posteriori Estimators
• Bayesian decision theory
• Linear classification and regression
• Model selection and evaluation
• Convex Optimization
• Kernel methods
• Societal Impact of Machine Learning
• Unsupervised learning (Clustering, Dimensionality Reduction)
• Introduction to Deep Learning

Prerequisites: The course is targeted to students in computer science, bioinformatics, math, and related areas with a mathematical background. Students should know linear algebra and have good basic knowledge of statistics, for example by having taken Mathematics for Computer Scientists I and II (for linear algebra) and Statistics Lab or Mathematics for Computer Scientists III (for statistics). In addition, prior attendance to machine learning related courses, e.g., Elements of Machine Learning, is considered as additional useful background.

Contact

We have prepared a Discord channel for you to discuss your questions and find study groups during the course: https://discord.gg/C8HBUx58rX

Please before reaching us out, check that the information is not available in the course description provided here and check with your peers via discord. We will also keep track of the Discord channel and will do our best to answer your questions.

For private/personal questions, please send us an email to: ml-course-team@lists.saarland-informatics-campus.de

Organizational Information

Lectures will start on April 19th! (one week after semester starts).

In the lectures we will cover the main theoretical aspects of the course, and in the Tutorials we will guide students through the resolution of exercises. There with be both theoretical and coding exercises. The main programming language used in the course will be Python (and PyTorch). Exercises are thought to help students preparing for the exam but there won't be assignments for the students to hand-in. Details on the tentative planning of the course.

Lectures*:  Mondays 14:15h & Wednesdays at 16:15h (on Zoom)

Tutorials*: (Tentatively) Thursdays at 12:15h (on Zoom)

Lectures and tutorials will be recorded and made available in Youtube. For further details on how to access the lectures please read carefully the following link.

Privacy disclaimer: We have decided to use zoom for both lectures and tutorials, as it provides superior functionality and usability for lecturing, including seamless live interaction and smooth integration of a whiteboard. We thus encourage you to  join the Zoom with your real name, your camera on,  and ask questions verbally. However, this is of course voluntary. If you are concerned about privacy, we encourage you to enter the zoom meeting under a nickname or pseudonym, and use only the textual chat for communication.

Evaluation

The course will be evaluated in a final exam (which will most likely take place in written form). There won't be intermediate evaluation or admission to the exam. However, over the semester, we will use the tutorials to jointly solve exercises in order to support students to prepare for the exam.

Exam and re-exam will take place in an online manner (most likely) and will take place, respectively on August 3rd from  2 p.m. - 5 p.m (registration deadline July 27th) and October 5th also from 2 p.m. - 5 p.m. (registration deadline September 28th).

If you are not able to register for the exam in HISPOS/LSF, please send us an email with your full name, matriculation number and study program to: ml-course-team@lists.saarland-informatics-campus.de

Bibliography