Machine Learning

News

Last minute exam preparation

Written on 18.07.25 by Peter Ochs

Dear all,

please understand that we do not support last-minute exam preparation and therefore, we will not answer further questions that are posted in the forum.

Best,

ML-Team

Final Exam Instructions

Written on 18.07.25 by Peter Ochs

Dear participants of the Main Exam,

here are the final instructions for the main exam on 21.07.2025:
- Read the following carefully !
- Students with family name starting with A -- G must wait in front of lecture hall HS002 in E1.3 at 9.15 o'clock.
- Students with family name starting with H -- Z must wait in front of Guenter--Hotz lecture hall E2.2 at 9.15 o'clock.
- The duration of the exam is 120 minutes.
- The exam is open book, which means that you may bring and use any (non-digital) material. You are not allowed to use any digital device or material. Your mobile phones, smart watches and the like must be switched off. Any attempt to cheat will result in the grade "failed" (5.0). This already includes the possession of forbidden material.

Required items:
- Student ID card.
- Non-erasable pen.
- Extra sheets of paper to make notes (to be submitted after the exam!).

Admitted items:
- Something to drink.
- Printed course material and handwritten notes.

We will ask you to enter the lecture hall (around 9.15 o'clock):
- Place your bag and any other material that is not admitted at the walls of the lecture hall.
- Take a seat where an exam sheet is placed. (Do not open the exam sheet !)
- Put your material on the desk. At all times, all material must be on the desk (not on neighboring chairs or below the desk !)
- Put your Student-ID card in front of you on the desk. (We check during the exam.)
- It is forbidden to copy the exam questions !

When all students are placed, we provide some additional instructions and officially start the exam (120 minutes).

During the exam,
- stay at your seat and focus on solving the exam questions.
- Raise your hand, if you have a question.
- Raise your hand, if you need to go to the restroom. (We have to note the timing.)

After the time of the exam has passed,
- stay at your seat until we have collected all exams and notes that you have written during the exam.
- Then the exam is over.

All the best,

ML-Team

Evaluation

Written on 23.06.25 by Armin Beck

Dear Students,

You are kindly invited to evaluate the Machine Learning lecture and exercise using the links provided below. Your feedback helps us to improve the course.

Please note that the evaluation will be available until July 6, 2025 (inclusive).

Best regards,
ML-Team

Course… Read more

Dear Students,

You are kindly invited to evaluate the Machine Learning lecture and exercise using the links provided below. Your feedback helps us to improve the course.

Please note that the evaluation will be available until July 6, 2025 (inclusive).

Best regards,
ML-Team

Course Title: Machine Learning - Exercise (1564411)
Evaluation Link: https://qualis.uni-saarland.de/eva/?l=1564411&p=8osr8c
Available until (inclusive): 06/07/2025

Course Title: Machine Learning - Lecture (156441)
Evaluation Link: https://qualis.uni-saarland.de/eva/?l=156441&p=s5a79t
Available until (inclusive): 06/07/2025

Tutorials

Written on 02.06.25 (last change on 02.06.25) by Armin Beck

Due to the public holiday on June 9th, there will be no tutorials on that day. Instead, we are offering an additional tutorial on Tuesday, June 10th, at 8:15 AM in lecture hall HS001, building E1.3.
We kindly ask all students from the Monday tutorials to attend this or one of the other available… Read more

Update to Project Instructions

Written on 02.06.25 by Armin Beck

We've added an important clarification regarding data and model usage for the image segmentation project. You can find the new section (2.3 Data and Model Usage Rules) in the updated PDF. Please make sure to read it carefully.

Lecture recording available

Written on 30.05.25 by Peter Ochs

Dear all,

since the lecture on 22.5. was cancelled, a video recording on the lecture "Performance Measures" was uploaded.

All the best,

ML-Team

Lecture 22.05.

Written on 22.05.25 by Armin Beck

Dear all,

We are sorry to inform you that today's lecture (22.05.2025) has been cancelled due to illness.

Thank you for your understanding.

All the best,

ML-Team

Written on 09.04.25 by Armin Beck

Tutorials

Due to the public holiday on April 21st, there will be no tutorials on that day. Instead, we offer an additional tutorial on Tuesday, April 22nd, at 8:15 in lecture hall HS001.
We kindly ask all students from the Monday tutorials to attend one of the other available tutorial sessions… Read more

Tutorials

SMART Hour

Please note the following changes regarding the SMART Hour:

Due to the public holiday, the SMART Hour originally scheduled for April 18th will be moved to April 16th at 12:15 in Günter-Hotz lecture hall.
On April 25th, the SMART Hour will take place in lecture hall HS II in building E.2.5.

Show all

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 from a theoretical point of view. After the lecture the students should be able to solve and analyze learning problems.

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, mathematics, and related areas with a mathematical background. Students should know linear algebra, calculus and have a good knowledge of statistics, for example by having taken Mathematics for Computer Scientists I and II and Statistics Lab or Mathematics for Computer Scientists III (for statistics). The course will be accompanied with programming exercises in Python, hence programming skills are expected. In addition, prior attendance to machine learning related courses, e.g., Elements of Machine Learning, is helpful but not required.

Organizational Information

Lectures: (start on April 10th)

Mondays: 14:15h at Building E2.2 -- Günter-Hotz Lecture hall I (0.01)
Thursdays: 12:15h at Building E2.2 -- Günter-Hotz Lecture hall I (0.01)

Tutorials (to pick between, start on April 21st, participation not mandatory):

Mondays: 12:15h at Building E1.3 -- HS002
Mondays: 16:15h at Building E1.3 -- HS002
Tuesday: 16:15h at Building E1.3 -- HS003
Wednesday: 08:15h at Building E1.3 -- HS003
Wednesday: 16:15h at Building E1.3 -- HS003

Exams: (no qualification requirement; except for registration in LSF)

Main exam: 21.7. from 9 am - 12 pm
Re-exam: 26.9. from 9 am to 12 pm

Bibliography

[Bach] Bach, F. Learning Theory from First Principles. Lecture Notes, available online, 2024.

[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.

[Klenke] Klenke, A. Probability Theory: A Comprehensive Course. Springer, 2006.

[Kallenberg] Kallenberg, O. Foundations of Modern Probability. Springer, 2021.