Probabilities and AIModule description #41321 / Version 1
- 6 CP
- Written exam
- Graded
- Winter semester
- German
| Module / Version | #41321 / #1 |
|---|---|
| Validity | Since Winter semester 2026/27 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Toussaint, Marc |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | German |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Technische Informatik und Mikroelektronik |
| Academic chair | 34342100 FG Intelligent Systems |
Contact
| Office | MAR 4-4 |
|---|---|
| Contact person | Toussaint, Marc |
| E-mail address | toussaint@tu-berlin.de |
| Website | https://argmin.lis.tu-berlin.de/ |
Learning outcomes
Students gain an understanding of the core concepts and relationships between probability, information, representation, and probabilistic data modeling. They learn to apply these principles to machine learning and sequential decision problems. In addition, they can translate mathematical formulations of relevant methods into implementations.
Content
* Basic concepts: information, entropy, description length, representation
* Multiple random variables and continuous random variables
* Optimality principles of probabilistic models: e.g., maximum likelihood, minimal description length, minimal cross-entropy, maximum entropy, priors, model complexity, regularization
* Probabilistic and neural models in ML: e.g., autoencoders, energy & diffusion models, conditional models
* Sequential decision problems: Monte Carlo tree search and reinforcement learning
* Multiple random variables and continuous random variables
* Optimality principles of probabilistic models: e.g., maximum likelihood, minimal description length, minimal cross-entropy, maximum entropy, priors, model complexity, regularization
* Probabilistic and neural models in ML: e.g., autoencoders, energy & diffusion models, conditional models
* Sequential decision problems: Monte Carlo tree search and reinforcement learning
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
Wahrscheinlichkeiten und Künstliche Intelligenz (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 2 h | 30 h |
| 60 h | |||
Wahrscheinlichkeiten und Künstliche Intelligenz (Exercise)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 2 h | 30 h |
| 60 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Exam preperation | 1 | 60 h | 60 h |
| 60 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Lecture: Traditional lecture.
Exercises: Homework assignments that can be solved on paper and correspond to the content of the final written exam; and discussion of these assignments.
Coding assignments: Practical programming tasks, submitted via an automated system.
Exercises: Homework assignments that can be solved on paper and correspond to the content of the final written exam; and discussion of these assignments.
Coding assignments: Practical programming tasks, submitted via an automated system.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Basic knowledge of probability at Abitur level
Basic knowledge of multivariate linear algebra and optimization
Basic knowledge of function networks and gradient rules
Basic knowledge of data structures and programming (incl. Python)
Basic knowledge of multivariate linear algebra and optimization
Basic knowledge of function networks and gradient rules
Basic knowledge of data structures and programming (incl. Python)
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 | German |
| Duration/Extent | 120 minutes |
Exam description
Prerequisites for Registering for the Module Exam
Passing the Programming and Homework Assignments:
Students must achieve an average of at least 50 % of the available points on both the programming and homework assignments.
Passing the Programming and Homework Assignments:
Students must achieve an average of at least 50 % of the available points on both the programming and homework assignments.
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
This module is not limited to a number of students.
Registration procedures
Registration for the course and programming assignments is via the ISIS page.
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 Science Computer Science (B. Sc.) - StuPO 2025 | WS 2026/27 | Pflichtbereich › Mathematisch-algorithmisch-konzeptionelle Kompetenzen |
Miscellaneous
Not specified