Einzelansicht eines Moduls

Modul (6 Credits)

Sustainability with Machine Learning

Name im Diploma Supplement
Sustainability with Machine Learning
Verantwortlich
Voraus­setzungen
Siehe Prüfungsordnung.
Workload
180 Stunden studentischer Workload gesamt, davon:
  • Präsenzzeit: 60 Stunden
  • Vorbereitung, Nachbereitung: 60 Stunden
  • Prüfungsvorbereitung: 60 Stunden
Dauer
Das Modul erstreckt sich über 1 Semester.
Qualifikations­ziele

Students will be able to

  • Assess use cases for machine learning within business environments
  • Develop an understanding of sustainability principles and their application in technological advancements.
  • Apply data preparation procedures, machine learning algorithms, and methodologies for training and evaluating models.
  • Explore deep learning architectures, including Vision and NLP models.
  • Discover how supply chain management, environmental monitoring, energy efficiency can be improved with the help of machine learning.
  • Recognise the ethical issues involved and how AI should be applied fairly in sustainability applications.
Prüfungs­modalitäten

Zum Modul erfolgt eine modulbezogene Prüfung in Form einer Klausur (in der Regel: 60-90 Minuten, 50% der Note) und eine Hausarbeit (5-10 Seiten, 50% der Note).
 

Verwendung in Studiengängen
  • WiInfVertiefungsstudiumWahlpflichtbereichVertiefungsrichtung "Modellierung und Realisierung betrieblicher Informationssysteme"5.-6. FS, Wahlpflicht
  • WiInfVertiefungsstudiumWahlpflichtbereich: Wirtschaftsinformatik und Informatik5.-6. FS, Wahlpflicht
Bestandteile
Name im Diploma Supplement
Sustainability with Machine Learning
Anbieter
Lehrperson
SWS
2
Sprache
englisch
Turnus
Wintersemester
maximale Hörerschaft
unbeschränkt
empfohlenes Vorwissen

The students should have a basic knowledge of information systems and be familiar with:

  • Programming languages such as Python. Good to know frameworks like Pytorch or Tensorflow (but not mandatory).
  • Mathematics and Statistics. Topics such as differentiation, matrix operations, vector spaces, and basic probability distributions will be relevant.
  • Data Analysis and Manipulation. Basics of data cleaning, transformation, and data analysis.
Abstract

Sustainability with Machine Learning explores the integration of machine learning techniques into sustainability domains to address environmental and social challenges. This course covers the foundations of machine learning, deep neural networks, and sustainable development applications. Students will gain knowledge of how machine learning may increase sustainability in decision-making, facilitate environmental monitoring, better supply chain management, and optimize energy efficiency. This course also reflects on using AI fairly and with ethical considerations in order to promote sustainable practices.

Lehrinhalte
  • Introduction to Sustainable Development
  • Fundamentals of Machine Learning
  • Deep Learning Architectures
  • Sustainable Supply Chain Management
  • Predictive Analytics for Energy Efficiency
  • Environmental Monitoring and Conservation
  • Ethical and Fair AI for Sustainability
Literaturangaben
  • Sustainability: A Comprehensive Foundation by Tom Theis and Jonathan Tomkin (eds.)
  • Introduction to Sustainable Development by Jennifer A. Elliott
  • Pattern Recognition and Machine Learning by Christopher M. Bishop
  • Machine Learning Yearning by Andrew Ng
  • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
  • Sustainable Supply Chains: A Research-Based Textbook on Operations and Strategy by Yann Bouchery, Charles J. Corbett, and Jan C. Fransoo
  • Predictive Analytics for Energy Efficiency Improvement by Sime Curkovic and Amir S. Gandomi
  • Environmental Monitoring Handbook by Frank R. Burden and Robert A. McDonnell
  • Artificial Intelligence for Good: How Technologies Can Save Our World by Rajiv Malhotra

Further literature will be provided during the course

didaktisches Konzept

There will be lectures in a traditional way, but students will have the opportunity to critically reflect on recently learned material during class discussions and engage with the lecturer in open discussion, enabling active student participation. Problem solving exercises along with some short practical tasks will be provided as assignments to the students in a student-centered approach where each student can assess their understanding of different topics. For more hands-on-experience and collaborative learning, there will be project-based learning from the mid of the semester in which students will work on an AI project in small teams which may culminate in presentations, reports, or prototypes.

Hörerschaft
Vorlesung: Sustainability with Machine Learning (WIWI‑C1219)
Name im Diploma Supplement
Sustainability with Machine Learning
Anbieter
Lehrperson
SWS
2
Sprache
englisch
Turnus
Wintersemester
maximale Hörerschaft
unbeschränkt
empfohlenes Vorwissen

See lecture

Abstract

See lecture

Lehrinhalte

See lecture

Literaturangaben

See lecture

didaktisches Konzept

The conceptual structure of these tutorials focuses primarily on assisting in assignments, development of the project, emphasize teamwork, group discussions, and presentation sessions.

Hörerschaft
Übung: Sustainability with Machine Learning (WIWI‑C1220)
Modul: Sustainability with Machine Learning (WIWI‑M0950)