Fairness, Accountability, and Transparency in Machine LearningModule description #40994 / Version 2
- 6 CP
- Portfolio examination
- Graded
- Winter and summer semester
- English
| Module / Version | #40994 / #2 |
|---|---|
| Validity | Since Summer semester 2025 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Berendt, Bettina |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Telekommunikationssysteme |
| Academic chair | 34332900 FG Internet und Gesellschaft |
Contact
| Office | HFT 8 |
|---|---|
| Contact person | Hanslik, Lelia Friederike |
| E-mail address | sekretariat@ias.tu-berlin.de |
| Website | https://www.tu.berlin/ias/studium-lehre/lehrveranstaltungen |
Learning outcomes
At the end of the course, students will be able to:
- Explain diverse narratives and conceptions around Machine Learning / AI and understand how they affect current research directions and implementations.
- Identify situations and socio-technical systems where automated decision-making is legitimate and where it is not.
- Discuss and apply key fairness and bias metrics and bias mitigation strategies in algorithmic decision-making and NLP, including explaining the impossibility theorem of fairness.
- Understand transparency measures such as model and data documentation and apply transparency techniques such as interpretable ML methods to analyze model decision-making processes and NLP.
- Explain concepts of accountability and recite current efforts in the EU to regulate AI / ML.
- Apply concepts of FAccT-ML to analyze and evaluate socio-technical systems and being able to conduct audit studies.
- Explain diverse narratives and conceptions around Machine Learning / AI and understand how they affect current research directions and implementations.
- Identify situations and socio-technical systems where automated decision-making is legitimate and where it is not.
- Discuss and apply key fairness and bias metrics and bias mitigation strategies in algorithmic decision-making and NLP, including explaining the impossibility theorem of fairness.
- Understand transparency measures such as model and data documentation and apply transparency techniques such as interpretable ML methods to analyze model decision-making processes and NLP.
- Explain concepts of accountability and recite current efforts in the EU to regulate AI / ML.
- Apply concepts of FAccT-ML to analyze and evaluate socio-technical systems and being able to conduct audit studies.
Content
Machine Learning (ML) systems and algorithmic decision making (ADM) systems are being adopted in a growing number of contexts. These systems are used to filter, sort, recommend, and personalize content/data. They are also increasingly used in making or informing decisions with major impact on individuals’ lives and subsequently the society like getting access to credit, insurance, health care, parol, and immigration.
This course focuses on computational and social perspectives on and methods of analysing and evaluating automated decision making and ML systems and its impacts. Concepts that will be studied in this course include biases and fairness, transparency measures such as explainability, interpretability and documentation of ML systems as well as evaluating and auditing ML Systems.
In summary, this course will cover the following topics:
- Overview of the field “Fairness, Accountability and Transparency (FAccT) in Machine Learning“
- Narratives around Machine Learning, Socio-technical systems and when is automated decision making legitimate?
- Notions of fairness, bias and fairness metrics and mitigation methods
- Fairness and NLP
- Transparency (Explainability, Interpretability, Documentation,..)
- Interpretability and NLP
- Accountability (Responsibilities, Audit studies, EU regulation, ML supply chain)
This course focuses on computational and social perspectives on and methods of analysing and evaluating automated decision making and ML systems and its impacts. Concepts that will be studied in this course include biases and fairness, transparency measures such as explainability, interpretability and documentation of ML systems as well as evaluating and auditing ML Systems.
In summary, this course will cover the following topics:
- Overview of the field “Fairness, Accountability and Transparency (FAccT) in Machine Learning“
- Narratives around Machine Learning, Socio-technical systems and when is automated decision making legitimate?
- Notions of fairness, bias and fairness metrics and mitigation methods
- Fairness and NLP
- Transparency (Explainability, Interpretability, Documentation,..)
- Interpretability and NLP
- Accountability (Responsibilities, Audit studies, EU regulation, ML supply chain)
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Fairness, Accountability, and Transparency in Machine Learning (FAccT-ML) | Integrated course | Summer semester | [en] | 4 | ISIS |
Workload and credit points
Fairness, Accountability, and Transparency in Machine Learning (FAccT-ML) (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 4 h | 60 h |
| Pre/post processing | 15 | 8 h | 120 h |
| 180 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The course is offered as “integrated classroom learning” comprising lectures, reading assignments, student presentations, and lab-based implementation. Students are required to acquire in-depth knowledge on select aspects through thorough self-study of current literature.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Students have a completed Machine Learning 1 or 2, Machine Intelligence 1 or 2, or equivalent ML or data science courses.
Student have a sufficient level of competency in English to follow and participate in discussions of Computer Science and interdisciplinary topics, to read scientific papers, and to write scientific essays. (At least CEFRL level B2 or equivalent.)
Student have a sufficient level of competency in English to follow and participate in discussions of Computer Science and interdisciplinary topics, to read scientific papers, and to write scientific essays. (At least CEFRL level B2 or equivalent.)
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 |
|---|---|---|---|
| Homework | 40 | written | 3 Homework |
| Project Implementation | 30 | practical | 6 Week Project Implementation |
| Project presentation | 30 | oral | 20 mins |
Exam description
Throughout the first two-thirds of the semester, there will be 3 small assessments, which may include both theoretical tests and practical homework assignments. In the final third of the semester, students will work on a practical project to demonstrate their understanding of FAccT-ML principles by applying them to analyze a real-world socio-technical system. This project will culminate in a graded presentation.
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 and summer semester.
Maximum number of participants
The maximum capacity of participants is 30.
Registration procedures
The registration procedure will be published and made available on the supplementary Web page of this module.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available – Fariness: https://fairmlbook.org/
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 (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems |
| WS 2025/26 | Wahlpflicht Studiengebiet B › Kognitive Systeme / Cognitive Systems | |
| SS 2026 | Wahlpflicht Studiengebiet B › Kognitive Systeme / Cognitive Systems | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet B › Kognitive Systeme / Cognitive Systems | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems |
| WS 2025/26 | Studiengebiete › Kognitive Systeme / Cognitive Systems | |
| SS 2026 | Studiengebiete › Kognitive Systeme / Cognitive Systems | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Kognitive Systeme / Cognitive Systems | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems |
| WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems | |
| SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Kognitive Systeme / 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 | SS 2025 | Wahlpflichtbereich › Fachstudium Wirtschaftsinformatik › Informationssysteme / Information Systems |
| WS 2025/26 | Wahlpflichtbereich › Fachstudium Wirtschaftsinformatik › Informationssysteme / Information Systems | |
| SS 2026 | Wahlpflichtbereich › Fachstudium Wirtschaftsinformatik › Informationssysteme / Information Systems | |
| WS 2026/27 | Wahlpflichtbereich › Fachstudium Wirtschaftsinformatik › Informationssysteme / Information Systems |
Miscellaneous
Materials will be made available online beginning at the start of the semester.