Hochschule Darmstadt - Fb Informatik

Drucken| Layout| Design| Schriftgröße English|
Module:Introduction to Artificial Intelligence
Module number:30.2596
Study programme:Bachelor 2014 - Katalog I: Anwendungs- und systemorientierte Module
Bachelor dual KoSI 2014 - Katalog I: Anwendungs- und systemorientierte Module
Bachelor KMI 2014 - Katalog I: Anwendungs- und systemorientierte Module
Type of course:VP = Lecture with integrated Practical
Weekly hours:4
Credit Points:5
Exam:written exam
Registering for examexplicitly and independent of booking
Frequency of offering:guest lecture (lastly in WS 2021/2022)
Required knowledge:Programming / Algorithms & Data Structures
Learning objectives:The students
  • know the different areas of Artificial Intelligence and their corresponding basic approaches and strategies
  • understand how AI applications are structured in principle
  • are able to use the appropriate technologies for given problems in order to solve non-trivial problems
  • can adapt methods to develop and realize proposals for solutions
  • can estimate where AI solutions are appropriate and can develop a critical view of progression in AI against the background of philosophical foundations and ethical questions as well as recognize and assess risks and possible technological consequences of the development of systems with AI technologies
Content:The lecture provides an overview of the areas of AI with references to in-depth courses. The following content is covered:
  • Machine learning (ML): Basic ML procedures based on prominent examples such as artificial neural networks or decision trees; Metrics / evaluation procedures for measuring the quality of ML predictions. Relation to symbolic and non-symbolic AI
  • Representation and processing of knowledge: basic procedures, e.g. Ontologies and linked data; Query languages and reasoning. Relation to symbolic and non-symbolic AI
  • Natural language processing (NLP): Application areas of NLP such as document classification, machine translation or human-machine communication, as well as current technologies for their implementation; Relation to symbolic and non-symbolic AI.
  • Computer vision: areas of application such as object recognition on images, as well as current technologies for implementing them; Relation to non-symbolic AI.
  • Cross-cutting issues: philosophical foundations and ethical questions of AI; Opportunities and risks of autonomous systems; Bias in AI applications; Effects of AI applications on society and working life.
All content is practiced in the practical
  • Bernhard G Humm: Applied Artificial Intelligence - An Engineering Approach. Second Edition. Leanpub, Victoria, British Columbia, Canada, 2016. leanpub.com/AAI
  • Russel, S. / Norvig, P. Artificial Intelligence: A Modern Approach (Pearson Series in Artificial Intelligence), 4. ed, 2020.

Weiterführende Literatur:
  • Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin, Heidelberg.
  • Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani: An Introduction to Statistical Learning. New York, NY, USA : Springer New York Inc., 2001 (Springer Series in Statistics, vol. 103)
  • Ian Goodfellow, Yoshua Bengio and Aaron Courville "Deep Learning", MIT Press 2016
  • Jurafsky, Daniel / Martin, James. 2014. Speech and Language Processing. An Introduction to Natural Language Processing, 2nd ed. Pearson India.
Lecture style / Teaching aids:Seminaristic lecture with integrated demonstrations,
lecture slides in digital format, additional examples, lab work
SWI Prolog: http://www​.swi-prolo​g.org/down​load/stabl​e​
Responsibility:Gunter Grieser
Released:WS 2021/2022

[Fachbereich Informatik] [Hochschule Darmstadt]
© 2008 - 2022 FBI OBS Team. Alle Rechte vorbehalten.