Data and Information Science

Neural Networks I: Architectures

Integrated course, 5.00 ECTS


Course content

Area 1: Basics and tools
- Repetition of natural neural networks
- Perceptron and linear separability
- Basic structures of artificial neural networks
- Multilayered Perceptron and error back propagation
- Hopfield Networks
- Markow Chain Monte Carlo Methods
- Tensors and tensor calculation
- Common frameworks for artificial neural networks
Area 2: Fields of application
- Time Series prediction
- Handwriting Recognition
- Associative Pattern Recognition
Area 3: Advanced Architectures
- Boltzmann Machines
- Self-organizing Cards
- Autoencoder
- Basics of Convolutional Neural Networks
- Basics of Recurrent Neural Networks

Learning outcomes

Students know and understand important basics in the field of artificial neural networks. They are also familiar with simple areas of application, with advanced architectures and with important frameworks.

Recommended or required reading and other learning resources / tools

Recommended literature or books:
- Aggarwal, C. (2018). Neural Networks and Deep Learning: A Textbook. Springer, 1st edition.
- Bishop, C.M. (2011). Pattern Recognition and Machine Learning, Springer, 1st edition.
- Engelbrecht, A.P. (2007). Computational Intelligence: An Introduction. Wiley, 2nd edition.
- Ertel, W. (2016). Basic course in Artificial Intelligence: A practical introduction. Springer, 4th edition.
- Kruse, R., Borgelt, C.m et al. (2015). Computational Intelligence: A methodical introduction to Artificial Neural Networks, Evolutionary Algorithms, Fuzzy Systems and Bayesian Networks. Springer-Vieweg, 2nd edition.
Recommended journals or selected articles:
Relevant journals and articles will be announced in the course.

Typical software for this module:
Python / Spyder / PyCharm / Scikit-learn / TensorFlow / Keras / PyTorch etc.

Mode of delivery

2,5 ECTS Lecture, 2,5 ECTS Exercise

Prerequisites and co-requisites

Module 1 and 5

Assessment methods and criteria

Lecture: final exam, Exercise: immanent test character