Intern
    Data Science Chair

    Theses and Practica

    The following pages show open topics for practica, bachelor and master theses, sorted by application fields. We will be happy to provide information on further open topics upon request. Topics can be completed either in English or German.

    Open Topics

    13.11.2024 | Physics & Deep Learning, Ecosystems

    Meteorological Downscaling Using Remote Sensing Data

    Global numerical climate models project meteorological quantities such as temperature, humidity, pressure, etc. decades into the future under the assumption of different emission scenarios. However, due to computational… Mehr
    11.11.2024 | Physics & Deep Learning, Ecosystems

    Resolution-Invariant Training of Deep Learning Athmospheric Models

    Athmosperic Circulation Models simulate the evolution of the state of the atmosphere and are used to generate weather forecasts or climate projections. Deep Learning has successfully been applied to learn the dynamics of the… Mehr
    24.05.2024 | Natural Language Processing

    Klassifikation von Romanen anhand von Emotions-Zeitreihen

    Romane gehören zu den Textarten, die trotz riesiger Fortschritte in den letzten Jahren die NLP immer noch vor Herausforderungen stellen: Selbst die neuesten Modelle sind nicht in der Lage, komplette Romantexte am Stück einzulesen… Mehr
    17.10.2023 | Physics & Deep Learning

    Can AI solve equations?

    Solving equations is hard. So hard that scientists have been developing new methods to do so for the past 2000 years and are still doing so. Why not use neural networks to do it? Mehr
    17.10.2023 | Physics & Deep Learning

    AI-driven scientific discovery

    Can Neural Networks become scientists? Imagine a future where machines, equipped with the ability to autonomously extract governing equations from empirical data, can catalyze breakthroughs in fields like climate science, quantum… Mehr
    13.10.2023 | Natural Language Processing

    Parameter Efficient Neural Networks

    As neural networks grow larger and more complex to solve new challenging tasks, they are often no longer able to run on end-user hardware and incur significant power and storage costs. For this reason, there is a need for… Mehr
    06.09.2023 | Publication Data

    Comparing Publication behavior in Germany

    Greetings prospective students, are you eager to dive into the fascinating world of scientific exploration? Well then, have I a project for you! I want to discover differences in research behavior in the German research landscape,… Mehr
    07.06.2023 | Physics & Deep Learning

    Data-efficient learning model on the intelligent bridge dataset

    As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them becomes significantly more expensive. In the case of sensor-based monitoring of infrastructures,… Mehr
    07.06.2023 | Physics & Deep Learning, Biological&Medical Data

    Improved Identification of Brain Activity to Predict Human Intelligence by using Machine Learning

    Human intelligence is the best predictor of important life outcomes like educational and occupational success and even health and longevity. Mehr
    07.06.2023 | Misc.

    Deep Metric Learning with Varying Similarity Definitions

    Deep Metric Learning (DML) trains a neural network that represents input data (e.g. images or texts) as an n-dimensional vector such that similar input items are close together in embedding space, while dissimilar items are… Mehr
    07.06.2023 | Physics & Deep Learning, Misc.

    Deep Music Composition

    Recent transformer-based generative language models have achieved near human-like performance in generating natural text. In this work, the applicability of these models to deep music generation is investigated. Mehr
    05.06.2023 | Security

    Anomaly Detection and the modelling of normality

    Unter Anomaly Detection verstehen sich Data-Mining Methoden um seltene Ereignisse (Anomalien) zu finden, die sich vom Großteil der Daten unterscheiden. Mehr
    05.06.2023 | Security

    Agent-based Simulation of Business Processes

    Für viele Anwendungen, wie Fraud Detection oder Process Monitoring werden Log-Daten von Geschäftsprozessen benötigt, um Modelle zu trainieren. Obwohl diese in modernen ERP Systemen automatisch aufgezeichnet und ausgewertet werden,… Mehr
    05.06.2023 | Misc.

    Semi-(un)supervised Learning mit vortrainierten Netzen

    In der Bildklassifikation und im Bereich des NLP gibt es eine Vielzahl vortrainierter Netze. Bei Bildern zählen VGG und ResNET in ihren verschiedenen Ausprägungen zu den Bekanntesten. Ziel dieser Arbeit (BA/MAP) ist es,… Mehr
    05.06.2023 | Physics & Deep Learning

    Unbiased characterization of tremor disorders using Deep Learning for time series analysis

    Massive time series feature extraction is a powerful tool to examine oscillating biological signals (Fulcher and Jones, 2017) such as tremor disorders. Tremor is defined as the involuntary, rhythmical, sinusoidal movement of a… Mehr
    05.06.2023 | Recommender Systems

    Language Modelle für Recommender Systeme

    Das Verständnis von Text ist auch ein wichtiger Bestandteil von Recommender Systemen, wenn sie auf Grundlage von textuellen Informationen Vorschläge generieren. Es hat sich gezeigt, dass Sprachmodelle/Language Modelle, die auf… Mehr
    05.06.2023 | Natural Language Processing

    Knowledge Graph Representation

    As one of their predominant research areas, the semantic web community builds knowledge graphs, which are machine-readable graphs that contain knowledge from all over the world wide web. Recently, researchers have shown great… Mehr