MLMMI - Machine Learning Model Management and InferenceModule description #41289 / Version 2
- 6 CP
- Portfolio examination
- Graded
- Summer semester
- English
| Module / Version | #41289 / #2 |
|---|---|
| Validity | Since Summer semester 2026 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Schelter, Sebastian |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34353500 FG Management von Data Science-Prozessen (BIFOLD) |
Contact
| Office | Not specified |
|---|---|
| Contact person | Not specified |
| E-mail address | Not specified |
| Website | Not specified |
Learning outcomes
- Identify the data management challenges in the model management and inference
- Design a model management strategy using registries to track model versions, lineage, and metadata for reproducibility
- Apply model compression techniques, including quantization and pruning
- Design an optimized model serving framework
- Monitor model performance issues in production
- Design a model management strategy using registries to track model versions, lineage, and metadata for reproducibility
- Apply model compression techniques, including quantization and pruning
- Design an optimized model serving framework
- Monitor model performance issues in production
Content
This advanced course focuses on the system and data management challenges in managing and serving machine learning (ML) models in production environments. The course starts by recapping standard ML pipelines up to the training stage. The lifecycle of an ML model extends far beyond training. Students will be introduced to foundational frameworks for model management, where trained models are treated as core data artifacts. The course covers data management techniques and optimizations, including model versioning, lineage tracking, and metadata management. Building on this, students will explore the architectures of modern model serving systems, along with performance optimizations such as dynamic batching, model compilation, and resource-efficient inference execution.
Furthermore, students will be exposed to state-of-the-art research on inference and model management. Through a combination of seminal research papers and hands-on projects, students will gain a comprehensive understanding of the entire model lifecycle beyond training, preparing them for both academic research and real-world system design.
Furthermore, students will be exposed to state-of-the-art research on inference and model management. Through a combination of seminal research papers and hands-on projects, students will gain a comprehensive understanding of the entire model lifecycle beyond training, preparing them for both academic research and real-world system design.
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
MLMMI - Machine Learning Model Management and Inference (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 3 h | 45 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 105 h | |||
MLMMI - Machine Learning Model Management and Inference (Exercise)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 1 h | 15 h |
| Pre/post processing | 15 | 2 h | 30 h |
| 45 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Project work | 7 | 3 h | 21 h |
| 21 h | |||
The workload of the module adds up to 171 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
- Lecture
- Working independently on e.g., a project or report
- Presentation
- Self-study
- Computer lab session/practical training
- Working independently on e.g., a project or report
- Presentation
- Self-study
- Computer lab session/practical training
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
- Completed bachelor degree
- Completed basic courses on applied machine learning, data management, and distributed systems
- Completed basic courses on applied machine learning, data management, and distributed systems
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) Programming assignment 1 | 10 | written | 1-2 weeks |
| (Deliverable assessment) Programming assignment 2 | 10 | practical | 1-2 weeks |
| (Deliverable assessment) Programming assignment 3 | 10 | practical | 1-2 weeks |
| (Deliverable assessment) Preparation of questions for lecture discussions | 10 | practical | 5-10 questions |
| (Deliverable assessment) Project presentation | 20 | oral | 15-25min (per group) |
| (Deliverable assessment) Project report (including code) | 40 | written | 4-6 pages |
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: Summer semester.
Maximum number of participants
The maximum capacity of participants is 24.
Registration procedures
Admission to the lecture is limited. Please take a look at https://deem.berlin/#teaching before the lecture period starts to get information on how you can register.
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 (M. Sc.) - StuPO 2015 | SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Data and Software Engineering / Data and Software Engineering | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering | |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2026 | WS 2026/27 | Engineering Sciences / Specialization › AI Engineering › Data and Software Engineering |
| Information Systems Management (Wirtschaftsinformatik) Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017 | SS 2026 | Wahlpflichtbereich › Fachstudium Informatik › Data and Software Engineering |
| WS 2026/27 | Wahlpflichtbereich › Fachstudium Informatik › Data and Software Engineering |
Computer Science (Informatik) (M. Sc.)
Studiengebiete: Data and Software Engineering
Computer Engineering (M. Sc.)
Studiengebiete: Data and Software Engineering
Electrical Engineering (M. Sc.)
Studiengebiete: Data and Software Engineering
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)
Studiengebiete: Data and Software Engineering
Studiengebiete: Data and Software Engineering
Computer Engineering (M. Sc.)
Studiengebiete: Data and Software Engineering
Electrical Engineering (M. Sc.)
Studiengebiete: Data and Software Engineering
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)
Studiengebiete: Data and Software Engineering
Miscellaneous
Not specified