M.184.5335 Real-World Machine Learning Projects | |
---|---|
(Real-World Machine Learning Projects) |
Koordinator (coordinator): | Prof. Dr. Oliver Müller |
Ansprechpartner (contact): | Prof. Dr. Oliver Müller (oliver.mueller[at]uni-paderborn.de) |
Credits: | 10 ECTS |
Workload: | 300 Std (h) |
Semesterturnus (semester cycle): | SoSe |
Studiensemester (study semester): | 1-4 |
Dauer in Semestern (duration in semesters): | 1 |
Lehrveranstaltungen (courses): | ||||||
---|---|---|---|---|---|---|
Zur Zeit sind keine Lehrveranstaltungen bekannt. (No courses are known.) | ||||||
Wahlmöglichkeiten innerhalb des Moduls (Options within the module): | ||||||
Keine |
Empfohlene Voraussetzungen (prerequisites): |
---|
Profound knowledge in the
field of machine learning (e.g. course „Data Science for Business“) and advanced
programming skills (Python). |
Inhalte (short description): |
---|
In research and academia, we often build machine learning (ML) models without embedding them in real-world applications or deploying them in production. Designing productive ML systems is both complex and unique. ML systems are complex because they consist of many components (e.g., big data, deep learning algorithms, high-performance computing infrastructure, interactive user interfaces) and involve many stakeholders (e.g., data scientists, managers, users). ML systems are unique because they are custom-built to solve a specific task (e.g., predict the probability that a customer will churn) and depend on proprietary data (e.g., behavioral data and transaction histories of a company’s customers). In this project-based module, students will learn how to develop, deploy, operate, monitor, and improve ML systems that solve real-world problems. As part of the projects, they will collaborate with external stakeholders (i.e., companies and research projects) to understand their business problems, gather and analyze requirements, and collect feedback. Lectures take place regularly during the lecture period, the module ends with the submission of the term paper and subsequent presentation after the lecture period. |
Lernergebnisse (learning outcomes): |
---|
Fachkompetenz Wissen (professional expertise): |
Studierende... |
Fachkompetenz Fertigkeit (practical professional and academic skills): |
Studierende... |
Personale Kompetenz / Sozial (individual competences / social skills): |
Studierende... |
Personale Kompetenz / Selbstständigkeit (individual competences / ability to perform autonomously): |
Studierende...
|
Prüfungsleistungen (examinations) | |||
---|---|---|---|
Art der Modulprüfung (type of modul examination): Modulprüfung | |||
Art der Prüfung (type of examination) |
Umfang (extent) |
Gewichtung (weighting) | |
a) | Hausarbeit | 20-30 Pages [Abgabe i.d.R. 15. August] | 60.00 % |
b) | Präsentation | 20 minutes [i.d.R. 7-14 Tage nach Abgabe] | 40.00 % |
Studienleistung / qualifizierte Teilnahme (module participation requirements) |
---|
Nein |
Voraussetzungen für die Teilnahme an Prüfungen (formal requirements for participating in examinations) |
---|
Keine |
Voraussetzungen für die Vergabe von Credits (formal requirements for granting credit points) |
---|
Die Vergabe der Credits erfolgt, wenn die Modulnote mindestens „ausreichend“ ist |
Gewichtung für Gesamtnote (calculation of overall grade) |
---|
Das Modul wird mit der Anzahl seiner Credits gewichtet (Faktor: 1) |
Verwendung des Moduls in den Studiengängen (The module can be selected in the following degree programmes) |
---|
M.Sc. Management Information Systems M.Sc. Wirtschaftsinformatik |
Umfang QT (participation requirements): |
---|
Lernmaterialien, Literaturangaben (learning material, literature): |
---|
Teilnehmerbegrenzung (participant limit): |
---|
20 Personen |
Sonstige Hinweise (additional information): |
---|
BITTE BEACHTEN!
PLEASE NOTE! NOTE: Since the participants work with confidential data of the practice partners during the seminar, confidentiality declarations may be requested from the companies. UNTERRICHTS-/PRÜFUNGSSPRACHE: Englisch/Deutsch
|