Module Artificial Intelligence, Computer Science (Master) (ER 7)

This lecture introduces current developments and research in the field of artificial intelligence and deep learning.

To start with, the foundations of neural networks are shortly repeated to be able to understand the following algorithms that are mainly based on deep learning.

Different architectures are introduced, like "Convolutional Neural Networks", "Recurrent Neural Networks" and "LSTMs", and their application in the context of "Computer Vision", "Natural Language Processing" and "Reinforcement Learning" are presented.

The outline of the lecture is as follows:

• Neural networks and deep learning 
• CNNs 
• Object detection, image segmentation
• Transfer learning
• Sequential models (RNNs, LSTMs, GRUs)
• Language models, word embeddings, neural machine translation
• Attention mechanism and transformer models
• Reinforcement Learning: Basics, Q-learning, DQNs, Alpha Go
• Autoencoders and GANs

This lab implements the theoretical foundations from the lecture into practical tasks.

For this, tasks from the following three domains are tackled:

* Computer Vision

* Natural Language Processing

* Reinforcement Learning

Requirements:

• Basic knowledge in Python
• Basic knowledge in Machine Learning