Students are familiar with advanced concepts of ANN such as generative networks, U-networks, autoencoder, but also alternative structures such as RBF networks, Bayes Deep Learning, and self-organizing maps (exemplary selection).
They are able to apply advanced deep-learning practices such as functional API, callbacks, monitoring deep learning boards to optimize their networks.
They know about batch normalization, hyperparameter optimization, advanced optimization algorithms (momentum , RSMProp, ADAM etc.) and model ensembling.
They can independently set up models at this level, implement and analyze in different platforms.

Completion of the predecessing module "Artificial Intelligence and Deep Learning (I)"

The module covers the following topics/contents:
Generative recurrent networks

• Text generation
• Style Transfer
• Variable Autoencoder
• Generative adversarial networks

• RBF-based networks
• Bayes Deep Learning
• Self Organizing maps

Lecture script as provided in the course (required)
Ian Goodfellow et all, Deep Learning, The MIT Press, 2016
Simon Haykin, Neural Networks and Learning Machines, Pearson, 2009
Francois Chollet, Deep Learning with Python, Manning,2nd ed. 2020
Gilbert Strange, Linear Algebra and Learning from Data, Wellesley Cambridge 2019
Specialist articles from arXiv.organd relevant journals from IEEE, Elsvier, etc.

Integrated course - teaching & discussion, demonstration, practical examples, group work in teams, home work

Immanent examination character: presentation, assignment reports, written/oral exam