Machine Learning 2-XModule description #41173 / Version 9
- 12 CP
- Written exam
- Graded
- Winter and summer semester
- English
| Module / Version | #41173 / #9 |
|---|---|
| Validity | Since Winter semester 2026/27 |
| Available language(s) | English, German |
| Credit points | 12 |
| Person responsible for the module | Müller, Klaus-Robert |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34352000 FG Maschinelles Lernen |
Contact
| Office | FR 6-1 |
|---|---|
| Contact person | Kauffmann, Jacob Reinhard |
| E-mail address | j.kauffmann@tu-berlin.de |
| Website | https://wiki.ml.tu-berlin.de/wiki/ |
Learning outcomes
Students have in-depth knowledge of the application of specific machine learning methods (classification, regression, dimensionality reduction, clustering) in selected application domains (e.g. bioinformatics, computer security) and are able to apply and further develop these methods independently. In particular, they are familiar with the aspects of machine learning that are decisive for practical success. In the elective component, they additionally engage actively and independently with a self-chosen complementary topic or methodological area of machine learning and deepen their understanding of it.
Content
This lecture deals with advanced topics of machine learning. Special emphasis is placed on the application. Several successful applications of machine learning will be discussed and the specifics of each will be addressed. Topics covered include: semi-supervised learning, boosting methods, optimization theory, kernel methods for structured data, graphical models.
Examples of successful applications include bioinformatics, computer security and text mining.
In addition, students can choose the following specializations in the compulsory elective course, depending on their previous knowledge and interests, e. g.:
• Mathematical foundations for machine learning: this course repeats, deepens and specializes the mathematical knowledge from the basic modules of the computer science degree.
• Machine Learning in the Sciences: in the respective additional lectures, the corresponding topic is further deepened theoretically
Examples of successful applications include bioinformatics, computer security and text mining.
In addition, students can choose the following specializations in the compulsory elective course, depending on their previous knowledge and interests, e. g.:
• Mathematical foundations for machine learning: this course repeats, deepens and specializes the mathematical knowledge from the basic modules of the computer science degree.
• Machine Learning in the Sciences: in the respective additional lectures, the corresponding topic is further deepened theoretically
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Maschinelles Lernen II | Integrated course | 0434 L 503 | Summer semester | [en] | 6 | ISIS |
Compulsory elective area
A selection of the following courses must be completed:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| AI for Biomedical Signal Analysis | Seminar | Winter semester | [en] | 2 | ISIS | |
| Bayesian Inference and Generative Modeling | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Classical Topics in ML | Seminar | 0434 L 588 | Winter semester | – | 2 | ISIS |
| Data-Driven Modeling in Statistical Physics | Seminar | Winter semester | [en] | 2 | ISIS | |
| Deep Learning on Graphs | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Explainable Machine Learning | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Generative Models | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Hot Topics In ML | Seminar | 0434 L 560 | Summer semester | – | 2 | ISIS |
| Machine Learning for Quantum Chemistry | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Machine Learning in Neuroscience | Seminar | Winter and summer semester | [de] | 2 | ISIS | |
| Machine Learning in Science and Industry, Lectures | Seminar | Winter and summer semester | [de] | 2 | ISIS | |
| Mathematische Grundlagen für Maschinelles Lernen | Course | 0434 L 545 | Winter and summer semester | – | 2 | WS 2026/27 (1) ISIS |
| Probabilistic Modeling and Inference | Seminar | Winter and summer semester | [en] | 2 | ISIS | |
| Representations in Machine Learning | Seminar | Winter and summer semester | – | 2 | ISIS | |
| Scientific applications in Machine Learning | Seminar | Winter and summer semester | – | 2 | ISIS | |
| Software engineering practices for scientific software development | Seminar | Winter and summer semester | [en] | 2 | ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (1)
Mathematische Grundlagen für Maschinelles Lernen (Course) 1
- Mathematische Grundlagen für Maschinelles Lernen (Math4ML) (Vorlesung) 1. Termingruppe 0434 L 545
Workload and credit points
Maschinelles Lernen II (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendence | 15 | 6 h | 90 h |
| Pre/post processing | 15 | 8 h | 120 h |
| Exam preperation | 1 | 60 h | 60 h |
| 270 h | |||
AI for Biomedical Signal Analysis (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Bayesian Inference and Generative Modeling (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Classical Topics in ML (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Data-Driven Modeling in Statistical Physics (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Deep Learning on Graphs (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Explainable Machine Learning (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Generative Models (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Hot Topics In ML (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Machine Learning for Quantum Chemistry (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Machine Learning in Neuroscience (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Machine Learning in Science and Industry, Lectures (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Mathematische Grundlagen für Maschinelles Lernen (Course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Probabilistic Modeling and Inference (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Representations in Machine Learning (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Scientific applications in Machine Learning (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Software engineering practices for scientific software development (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 1710 hours. The module therefore comprises 12 credit points.
Description of teaching and learning methods
weekly lectures, tutorials, and homeworks
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Basic knowledge in linear algebra and calculus.
Basic knowledge in probability theory.
Basic programming knowledge, programming in Python.
Machine Learning 1 or equivalent.
Basic knowledge in probability theory.
Basic programming knowledge, programming in Python.
Machine Learning 1 or equivalent.
Mandatory requirements for the module examination registration:
The examination requirements could not be retrieved.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English |
| Duration/Extent | 120 minutes |
Exam description
Certificate of achievement (englisch):
Admission to the module examination requires the non-graded certificate „[ML] Non-graded certificate for elective" from the chosen elective course. Scope and passing criterion depend on its teaching format:
• Seminar (SE): Scope: one oral presentation (approx. 30 minutes) on an assigned topic.
Passing criterion: presentation passed.
• Course (KU): Scope: a written test (90 minutes).
Passing criterion: 50 % of the achievable points.
Admission to the module examination requires the non-graded certificate „[ML] Non-graded certificate for elective" from the chosen elective course. Scope and passing criterion depend on its teaching format:
• Seminar (SE): Scope: one oral presentation (approx. 30 minutes) on an assigned topic.
Passing criterion: presentation passed.
• Course (KU): Scope: a written test (90 minutes).
Passing criterion: 50 % of the achievable points.
Duration of the module
The following number of semesters is estimated for taking and completing the module: 2 semester(s).
This module can be started in the following semesters: Winter and summer semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
Please visit the course website for more information.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
No recommended literature given
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Biomedical Engineering StuPO 2018 | WS 2026/27 | 2. Wahlpflichtmodule › 2.2 Ingenieurwissenschaftliche Vertiefungen |
| Computational Engineering Science (Informationstechnik im Maschinenwesen) StuPO 2018 (17.01.2018) | WS 2026/27 | 1. Kernbereich 1: Informatik und Mathematik |
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Studiengebiet B › Kognitive Systeme / Cognitive Systems |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Kognitive Systeme / Cognitive Systems |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
| Engineering Science StuPO 2020 | WS 2026/27 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2015 | WS 2026/27 | Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Cognitive Systems |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2026 | WS 2026/27 | Engineering Sciences / Specialization › AI Engineering › Cognitive Systems |
| Information Systems Management (Wirtschaftsinformatik) Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017 | WS 2026/27 | Wahlpflichtbereich › Fachstudium Wirtschaftsinformatik › Informationssysteme / Information Systems |
Miscellaneous
The mandatory part ("Pflichtgruppe") is only offered during the summer term. However, it is possible to participate in some electives during the winter term.
Credits from individual courses that have already been counted towards completed modules cannot be applied twice.
Credits from individual courses that have already been counted towards completed modules cannot be applied twice.