Interpretable Machine LearningModule description #41130 / Version 1
- 6 CP
- Portfolio examination
- Graded
- Winter semester
- English
| Module / Version | #41130 / #1 |
|---|---|
| Validity | Since Winter semester 2026/27 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Samek, Wojciech |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34352800 FG Maschinelles Lernen und Kommunikation |
Contact
| Office | EN 16 |
|---|---|
| Contact person | Samek, Wojciech |
| E-mail address | wojciech.samek@tu-berlin.de |
| Website | https://iphome.hhi.de/samek/#Teaching |
Learning outcomes
Upon successful completion of the module, students are able to define and distinguish key concepts of interpretability, explainability, and transparency in machine learning. They can critically analyze and evaluate the limitations and risks of modern machine learning methods with regard to explainability, and identify and assess real-world application scenarios in which a lack of explainability leads to issues in usability, trust, or decision-making. Furthermore, they are able to select, apply, and compare appropriate methods to improve interpretability, and to systematically evaluate models with respect to their explainability and critically reflect on the results. Students are also able to classify and discuss current challenges and research directions in explainable AI. In addition, they can independently research, analyze, and structure scientific literature, and present their own results effectively in written and oral form.
Content
The module consists of a lecture and a seminar.
The lecture provides the methodological foundations of explainable machine learning systems. A central focus is on explanation methods, i.e., techniques that make a model's functioning and the basis of its predictions transparent. The lecture covers different types of explanation methods, discusses their advantages and limitations, and explains the theoretical foundations.
In the accompanying seminar, students engage with current research in the field of interpretable machine learning. They develop skills in handling scientific literature, writing research papers, and presenting their findings.
The lecture provides the methodological foundations of explainable machine learning systems. A central focus is on explanation methods, i.e., techniques that make a model's functioning and the basis of its predictions transparent. The lecture covers different types of explanation methods, discusses their advantages and limitations, and explains the theoretical foundations.
In the accompanying seminar, students engage with current research in the field of interpretable machine learning. They develop skills in handling scientific literature, writing research papers, and presenting their findings.
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
Interpretable Machine Learning (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Interpretable Machine Learning (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 3.3 h | 49.5 h |
| Presentation and report | 5 | 2 h | 10 h |
| 89.5 h | |||
The workload of the module adds up to 179.5 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The module consists of a lecture and a seminar.
In the two-hour lectures, the instructor presents, discusses, and illustrates the material with examples in a traditional lecture format. The lectures take place weekly during the winter semester.
In the seminar, a specific topic area is worked on individually. Under guidance, students learn scientific research methods and prepare a professional presentation. The seminar includes a written report and concludes with an individual presentation, which is evaluated in terms of content and didactics and accompanied by feedback.
In the two-hour lectures, the instructor presents, discusses, and illustrates the material with examples in a traditional lecture format. The lectures take place weekly during the winter semester.
In the seminar, a specific topic area is worked on individually. Under guidance, students learn scientific research methods and prepare a professional presentation. The seminar includes a written report and concludes with an individual presentation, which is evaluated in terms of content and didactics and accompanied by feedback.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Programming skills, a good grounding in mathematics, particularly linear algebra and calculus.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| (Deliverable assessment) Presentation (Seminar) | 30 | practical | 20 Minutes |
| (Deliverable assessment) Written Report (Seminar) | 20 | written | 3-5 Pages |
| (Examination) Written Exam (Lecture) | 50 | written | 60 Minutes |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
The maximum capacity of participants is 20.
Registration procedures
Registration takes place one week before the first lecture and must be completed via the module’s ISIS course.
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 |
|---|---|---|
| Computer Engineering Computer Engineering (B. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Kataloge › Informatik |
| Computer Science Computer Science (B. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Katalog Informatik |
| Computer Science Computer Science (B. Sc.) - StuPO 2025 | WS 2026/27 | Wahlpflichtbereich › Studiengebiete › Intelligente Systeme › Seminare |
| Information Systems Management Information Systems Management (B. Sc.) - StuPO 2015 | WS 2026/27 | Wahlpflichtbereich › Informatik |
| Information Systems Management Information Systems Management (B. Sc.) - StuPO 2021 | WS 2026/27 | Wahlpflichtbereich › Informatik |
| Information Systems Management Information Systems Management (B. Sc.) - StuPO 2025 | WS 2026/27 | Wahlpflichtbereich › Vertiefung Informatik › Seminare |
Miscellaneous
Not specified