Neural Networks II: Deep Learning

Course content

Part 1: Advanced topics regarding neural networks
- Convolutional Neural Networks
- Recurrent Neural Networks
- Generative Adversarial Networks
Part 2: Advanced applications of neural networks
- Handwriting and speech recognition
- Edge detection in pictures and videos
- Object recognition in pictures and videos
Part 3: Deep learning in practice
- Deep learning frameworks for CPU, GPU and TPU computing
- Planning, conception, setup as well as training and optimization of neural networks

Learning outcomes

The students understand advanced topics regarding neural networks and are able to plan and design, set up, train and optimize neural networks for specific tasks (especially for handwriting and speech recognition as well as edge and object recognition).

Recommended or required reading and other learning resources / tools

Recommended literature or books:
- Aggarwal, C. C. (2018). Neural Networks and Deep Learning: A Textbook. Springer, 1st edition.
- Bishop, C. M. (2011). Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, 1st edition (reprint 2011).
- Deru, M., Ndiaye, A. (2019). Deep Learning mit TensorFlow, Keras und TensorFlow.js: Einstieg, Konzepte und KI-Projekte mit Python, JavaScript und HTML5. Rheinwerk Computing, 1. Auflage.
- Engelbrecht, A. P. (2007).Computational Intelligence: An Introduction. Wiley, 2nd edition.
- Ertel, W. (2016). Grundkurs Künstliche Intelligenz: Eine praxisorientierte Einführung (Computational Intelligence). Springer Vieweg, 4. Auflage.
- Kruse, R., Borgelt, C. et al (2015). Computational Intelligence: Eine methodische Einführung in Künstliche Neuronale Netze, Evolutionäre Algorithmen, Fuzzy-Systeme und Bayes-Netze. Springer Vieweg, 2. Auflage.
- Pfister, B., Kaufmann, T. (2017). Sprachverarbeitung: Grundlagen und Methoden der Sprachsynthese und Spracherkennung. Springer Vieweg, 2. Auflage.
Recommended journals or selected articles:
Relevant journals and articles will be announced in the courses.

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

Mode of delivery

1,25 ECTS Lecture, 1,25 ECTS Exercise

Prerequisites and co-requisites

Module 7,8,9 and 10

Assessment methods and criteria

Lecture: final exam; Exercise: examination character