Artificial Intelligence (New since Term 2026)

This lecture introduces in the categories and concepts of artificial intelligence, machine learning, deep learning and partiularly Large Language Models. The second block introduces into Chatbots, RAG systems and AI agents. And a third block shows how LLMs can be integrated into Python implementations of AI agents.

Natural Language Processing

Introduces conventional and modern techniques which enable computers to understand written natural language: Crawling, text-preprocessing, language models etc. The realisation of NLP applications, such as text-classification, Named Entity Recognition, Question Answering, Translation etc. is discussed.

Selected Topics of AI

This lecture introduces in programming deep neural network applications with PyTorch. First, the basic concepts of PyTorch are introduced. Then sample neural network applications of the domains 1.) structured data, 2.) images and 3.) texts are implemented.

Old Artificial Intelligence up to Term 2025/2026

Introduces into the main concepts and algorithms of the four AI categories: Search & Plan, Knowledge & Inference, Modelling of Uncertainty and Machine Learning.

Machine Learning

Introduces the concepts and algorithms of conventional machine learning and deep learning. Modern neural network architectures such as CNNs, Autoencoder, GANs, Diffusion-Models, Transformer, DQN are introduced.

Object Recognition

Introduces the concepts and algorithms of conventional object recognition and Deep Learning based object recognition, including image classification, object detection and instance segmentation, image generation.

Object Recognition

Short Intro to Pytorch, which is applied in the CSM lecture Programming Deeplearning Algorithms. The longer Pytorchtutorial is in the section Selected Topics of AI above.

Python for Data Science

First basic Python concepts like data structures, control structures, functions, classes etc. are introduced. In the second part the most important packages for Data Science, e.g. Numpy, Pandas, Matplotlib, Plotly are applied.

Machine Learning

Implementation of conventional Machine Learning with scikit-learn and of Deep Learning with tensorflow and keras.

Basics of Probability Theory

Basic concepts and notions of Probability Theory and Statistics.

Basic Maths for AI and ML

Basic Maths for Artificial Intelligence and Machine Learning

Computer Vision with PyTorch

Outdated versions. Currently not used in any lecture.

AI Introduction

Basic concepts and applications of the 4 AI categories: Search & Plan, Knowledge & Inference, Modelling of Uncertainty and Machine Learning.

a. ML for structured data

Conventional ML algorithms.

b. ML for image and video

Deep Learning algorthms for vision, e.g. CNNs...

c. ML for sequential data and text

Deep learning for sequences, e.g. RNNs, Transformer, ...

a. ML for structured data

Implementation with scikit-learn.

b. ML for image and video

Implementation with Tensorflow and Keras.

c. ML for sequential data and text

Implementation with Tensorflow and Keras.