News
Mid-term ScheduleWritten on 18.05.26 by María Martínez-García Dear students, Given the number of students registered for the mid-term exam, we have decided to split the exam into two time slots:
Students have been assigned to the slots based on their matriculation numbers (in descending… Read more Dear students, Given the number of students registered for the mid-term exam, we have decided to split the exam into two time slots:
Students have been assigned to the slots based on their matriculation numbers (in descending order):
You can find the complete student lists and seating plans in the “Organization” folder under the course materials. Please note that the exam itself will last 30 minutes. To hand in your exam, you must present either your student card or another valid photo ID for verification. You will also need to provide your matriculation number. Remember that this exam is closed-book. No cheat sheets or additional materials are permitted. However, the use of a non-programmable scientific calculator is allowed. If you have any questions, please contact us via the forum. Best regards, |
Tutorials on the following weeksWritten on 13.05.26 by María Martínez-García Dear students, There has been some confusion regarding the tutorial schedule for the next two weeks. The team has decided to proceed with tutorials next week, so you will have the opportunity to ask questions before the mid-term. To clarify:
Dear students, There has been some confusion regarding the tutorial schedule for the next two weeks. The team has decided to proceed with tutorials next week, so you will have the opportunity to ask questions before the mid-term. To clarify:
Best regards, ML team |
Mock Exam (mid-term) ReleasedWritten on 12.05.26 by María Martínez-García Dear students, We have uploaded a mock exam together with solutions to help you prepare for next week’s mid-term (admission) exam. You can find the materials in the “Exam preparation” folder. We hope this helps you! Please keep in mind that the mock exam questions are intended solely as… Read more Dear students, We have uploaded a mock exam together with solutions to help you prepare for next week’s mid-term (admission) exam. You can find the materials in the “Exam preparation” folder. We hope this helps you! Please keep in mind that the mock exam questions are intended solely as preparation material and do not define the exact scope or content of the exam, so do not overfit to them! All topics covered in lectures, tutorials, and the shared course materials from Blocks I and II are considered part of the exam content. Also, please remember to register on CMS if you plan to take the mid-term exam (no registration in LSF is necessary). Best, |
MID-TERM EXAM -- Important Information, please read carefully!Written on 07.05.26 by Isabel Valera Dear ML'26 students, As you know the mid-term (admission) exam is approaching. We have now open the registration on CMS Not registration on LSF necessary). Please register until May 15, 23:59 (German time) for the mid-term (admission exam) if you intend to officially participate in the… Read more Dear ML'26 students, As you know the mid-term (admission) exam is approaching. We have now open the registration on CMS Not registration on LSF necessary). Please register until May 15, 23:59 (German time) for the mid-term (admission exam) if you intend to officially participate in the lecture, via the registration page: https://cms.sic.saarland/ml26/registration_items Passing the mid-term exam is a mandatory requirement for admission to the final exam and the re-exam. Students who do not take or do not pass the mid-term exam will not be eligible to participate in the final exam. Information on the mid-term (admission) exam format:
Next week, we will share a set of sample exam-style questions to help students prepare for the exam. For any question, please come to the lectures or ping us in the Forum. Best regards, Prof. Valera
|
Block 2 Materials ReleasedWritten on 30.04.26 by Kunchangtai Liang Dear students, We have released the Exercise Sheet 2.1 and 2.2 and Programming Tutorial 2.1 and 2.2 for the second block. Next week (from 4 May) we will start with Sheet 2.1 and the following week (11 May) Sheet 2.2. In the third week (18 May) we will cover both programming exercises. Have a… Read more Dear students, We have released the Exercise Sheet 2.1 and 2.2 and Programming Tutorial 2.1 and 2.2 for the second block. Next week (from 4 May) we will start with Sheet 2.1 and the following week (11 May) Sheet 2.2. In the third week (18 May) we will cover both programming exercises. Have a nice day! Your ML Team |
Block 1 Materials releasedWritten on 18.04.26 (last change on 18.04.26) by Thuc Khanh Huyen Vo Dear all, We have released the Exercise Sheet 01 and Programming Tutorial 01 for the first block. The first tutorial next week will cover the programming part. In the meantime, you are welcome to look through the exercise part in preparation for the following tutorial. Have a nice weekend! Your ML Team |
Welcome & Getting readyWritten on 08.04.26 (last change on 08.04.26) by Isabel Valera Dear all, Welcome to the Machine Learning lecture of the SoSe26. As you may know, the lecture will start at 2.15pm in the GHH on April 13, when I will also share the organizational details of the course. In the meantime, we have uploaded some background materials for you to revise and get ready… Read more Dear all, Welcome to the Machine Learning lecture of the SoSe26. As you may know, the lecture will start at 2.15pm in the GHH on April 13, when I will also share the organizational details of the course. In the meantime, we have uploaded some background materials for you to revise and get ready for the course content. You can also see the tentative schedule for the course at the bottom of the page. See you on Monday, Prof. Isabel Valera
|
Machine Learning
In this course we will introduce the mathematical 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 from a theoretical point of view. 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 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.
Organizational Information
Lectures:
- Mondays at 14:15h -- Building E2.2, Günter-Hotz Lecture hall I (0.01)
- Thursdays at 12:15h -- Building E2.2, Günter-Hotz Lecture hall I (0.01)
Lectures will start on April 13th!
Tutorials (to pick between):
- Mondays at 12:15h -- Building E1.3, Room HS002
- Mondays at 16:15h -- Building E1.3, Room HS001
- Tuesdays at 10:15h -- Building E1.3, Room HS001
- 05.05.26 and 07.07.26 at Building E2.2, Room GHH
- Tuesdays at 12:15h -- Building E1.3, Room HS002
- Wednesdays at 14:15h -- Building E1.3, Room HS002
- Wednesdays at 16:15h -- Building E1.3, Room HS002
- 06.05.26 at Building E1.3, Room HS001
Tutorials will start on April 20th!
Exams:
- Mid-term (admission) exam: 21.05.2026 -- Information on the mid-term (admission) exam format:
- The exam duration will be approximately 30 minutes and will take place within the 12:00–14:00 time slot on May 21st. The exact starting time of exam will be communicated to students after registration.
- The exam will consist of a multiple-choice test with a total of 15 questions, worth 20 points overall.
- The passing grade, i.e., the admission threshold, is 10 out of 20 points.
- Each question will have at least one correct answer. Full points for a question will only be awarded if all correct answers are selected. Partially correct or incomplete answers will receive zero points. There is no penalty for incorrect answers.
- Please note that this is an ungraded exam. Its sole purpose is to determine eligibility for participation in the lecture and admission to the final exam (and re-exam).
- The exam will include both numerical and conceptual questions covering Blocks I and II. All material discussed in lectures, tutorials, and shared course materials from these blocks is considered part of the exam content.
- The exam will be close-book. We will provide equations when needed, but you are expected to recognize and understand the key formulas introduced in the course.
- Main exam: 04.08.2026
- Re-exam: 28.09.2026
Tentative Schedule:
| Week | Date | Lecture Nr. | Title | |
|
1. Introduction to ML |
1 | 13-Apr | 1 | Introduction |
| 1 | 16-Apr | 2 | Bayesian Decision Theory | |
| 2 | 20-Apr | 3 | Empirical Risk Minimization | |
| 2 | 23-Apr | No Class | ||
|
2. Linear Supervised ML |
3 | 27-Apr | 4 | Linear Regression I |
| 3 | 30-Apr | 5 | Linear Regression II | |
| 4 | 4-May | 6 | Linear Classification | |
| 4 | 7-May | 7 | Performance Measures I | |
| 5 | 11-May | 8 | Performance Measures II | |
| 5 | 14-May | Holiday | No Class | |
| 6 | 18-May | Introduction to Project | ||
| 6 | 21-May | Mid-term Exam | ||
| 7 | 25-May | Holiday | No Class | |
|
3. Unsupervised Learning |
7 | 28-May | 9 | Clustering |
| 8 | 1-Jun | 10 | Dimensionality Reduction | |
| 8 | 4-Jun | Holiday | No class | |
|
4. SVM and kernel methods |
9 | 8-Jun | 11 | Convex Optimization I |
| 9 | 11-Jun | 12 | Convex Optimization II | |
| 10 | 15-Jun | 13 | Linear SVM | |
| 10 | 18-Jun | 14 | Intro to Kernels | |
| 11 | 22-Jun | 15 |
Learning with Kernels |
|
| 11 | 25-Jun | No Class / Maybe Q&A | ||
|
5. Deep learning |
12 | 29-Jun | 16 | Deep Learning I - Feedforward Nets + BP |
| 12 | 2-Jul | 17 | Deep Learning II - CNNs | |
| 13 | 6-Jul | 18 |
Deep Learning III - Transformers |
|
| 13 | 9-Jul | 19 |
Beyond Supervised DL, and Q&A |
|
|
6. Societal impact |
14 | 13-Jul | 20 | Societal Impact |
| 14 | 16-Jul | 21 | Explainability & Interpretability |
Bibliography
[Bishop] Bishop, C. M. Pattern recognition and machine learning. Springer, 2006
[DSH] Duda, R. O., Hart, P.E., and Stork, D.G. Pattern classification (2nd edition). Wiley-Interscience 2000
[Boyd] Boyd, S., Boyd, S. P., and Vandenberghe, L. . Convex optimization. Cambridge university press, 2004
[eML] Hastie, T., Tibshirani, R., and Friedman, J. The Elements of Statistical Learning. Springer, 2009.
[Kernels] Smola, A. J., & Schölkopf, B. Learning with kernels. GMD-Forschungszentrum Informationstechnik, 1998.
[DL] Goodfellow, I., Courville, A., and Bengio, Y. Deep learning. MIT press, 2016.
[DL] Simon J.D. Prince Understanding Deep Learning. MIT press, 2023.
[DL] Bishop, C. M. & Bishop, H Deep Learning: Foundations and Concepts. Springer, 2024.
