|
Lecturer(s)
|
-
Kästner Wolfgang, prof. Dr. Ing.
|
|
Course content
|
The content: - foundations of Artificial Intelligence (AI) / Artificial Neural Networks (ANN) - application of AI / ANN for modelling and classification - modelling based on Multilayer Perceptron (MLP) - MLP - structure, demonstration example, software - classification based on Kohonen Maps (Self Organizing Maps, SOM) - SOM - structure, demonstration example, software - applications
|
|
Learning activities and teaching methods
|
Lecture, Practicum
- Class attendance
- 56 hours per semester
- Preparation for exam
- 44 hours per semester
- Preparation for credit
- 20 hours per semester
- Home preparation for classes
- 30 hours per semester
|
|
Learning outcomes
|
The methodical aspects of the topic will be communicated by lectures. Seminars and exercises as well as practical courses at PC tool serve for consolidation of knowledge.
|
|
Prerequisites
|
Mathematics
|
|
Assessment methods and criteria
|
Combined examination
No condition of registration
|
|
Recommended literature
|
-
Beer, W. Applied Artificial Intelligence: Neural networks and deep learning with Python and TensorFlow. Amazon Digital Services LLC, 2017.
-
Duval, F. Artificial Neural Networks: Concepts, Tools and Techniques explained for Absolute Beginners (Data Sciences). CreateSpace Independent Publishing Platform, 2018.
|