Stud.IP Uni Oldenburg
University of Oldenburg
29.11.2023 20:42:18
inf536 - Computational Intelligence II (Complete module description)
Original version English PDF download
Module label Computational Intelligence II
Module abbreviation inf536
Credit points 6.0 KP
Workload 180 h
Institute directory Department of Computing Science
Applicability of the module
  • Master Applied Economics and Data Science (Master) > Data Science
  • Master's Programme Business Informatics (Master) > Akzentsetzungsmodule der Informatik
  • Master's Programme Computing Science (Master) > Angewandte Informatik
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Embedded Brain Computer Interaction
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Human-Computer Interaction
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Systems Engineering
  • Master's Programme Environmental Modelling (Master) > Mastermodule
Responsible persons
  • Kramer, Oliver (module responsibility)
  • Lehrenden, Die im Modul (Prüfungsberechtigt)
Prerequisites
useful previous knowledge: Linear Algebra, Stochastics
Skills to be acquired in this module

In the lecture "Convolutional Neural Networks" you will learn the basics of Convolutional Neural Networks, from methodological understanding to implementation.
Professional competence
The Students:

  • will learn Deep Learning expertise, which are essential qualifications as AI experts and Data Scientists.

Methodological competence

The Students:

  • learn the methods mentioned as well as the implementation in Python, NymPy and Keras.
Social competence
The Students:
  • are encouraged to discuss the taught content in groups and work together to implement the programming tasks in the exercises

Self-competence
The Students:
  • are guided to conduct independent research on advanced methods as the teaching field changes dynamically
Module contents
Students learn the basics of machine learning and in particular the topics of dense layers, cross-entropy, backpropagation, SGD, momentum, Adam, batch normalization, regularization, convolution, pooling, ResNet, DenseNet, and convolutional SOMs
Recommended reading
  • Deep Learning by Aaron C. Courville, Ian Goodfellow und Yoshua Bengio
Links
Language of instruction English
Duration (semesters) 1 Semester
Module frequency every summer term
Module capacity unlimited
Module level
Type of module
Teaching/Learning method 1VL + 1Ü
Previous knowledge nützliche Vorkenntniss: Lineare Algebra, Stochastik
Type of course Comment SWS Frequency Workload of compulsory attendance
Lecture 2 SoSe 28
Exercises 2 SoSe 28
Total module attendance time 56 h
Examination Examination times Type of examination
Final exam of module
lecture-free period at the end of the semester
written exam, e-exam