Individual thesis topics
We are looking for students who would like to work on our future research projects. Depending on your skills and future plans, we will work together to find a topic in our research areas that best suits you. In your thesis, you will come into contact with emerging topics with a focus on AI. The following topics are examples of what such work might look like.
Suggested topics
-
Diffusion Transformer (DiT) for conditional learning curve generation [B.Sc / M.Sc]
Diffusion models are typically used to generate images, possibly conditioned with text. In this thesis, a Diffusion Transformer (DiT) will be adapted to learn to generate learning curves based on hyperparameter queries, using real learning curves from benchmark problems. Essentially, this model aims to generate new multi-fidelity optimization problems and implicitly learn both the cross-correlation of multiple learning curves based on their hyperparameters and the stochastic properties of learning curves derived from their time-series characteristics.
Depending on the progress of the work, targeted generalization can also be considered, such as the iterative querying of additional hyperparameter configurations, which would be analogous to generating new image patches.
This work has several derivative applications, particularly the artificial generation of multi-fidelity optimization benchmark problems based on the properties of real curves.
Contact: Tim Ruhkopf
-
Auto-PyTorch for X [BSc + MSc]
Extend, apply and refine our AutoDL tool Auto-PyTorch for new areas such as outlier detection, maintenance prediction or time series prediction. We recommend a strong background in machine learning (especially Deep Learning) and their chosen application for this work. When applying, please indicate the direction you would like to work in and provide a rough plan of how you would implement AutoPytorch in your target area.
Contact: Difan Deng
-
Implementation of a new DAC benchmark [BSc + MSc].
Modelling, implementation and evaluation of DAC for any target algorithm. We recommend a strong background in RL, basic knowledge of DAC, and the target domain of your choice to be successful in this topic. Possible target domains include machine learning or reinforcement learning, MIPS or SAT solvers, and evolutionary algorithms.
Contact: Theresa Eimer
-
Policy Similarity in Contextual Reinforcement Learning [Bsc + Msc]
Scaling up Reinforcement Learning to complex environments, beyond games like chess, requires biasing our methods to address large state and action spaces and complicated dynamics. Policy similarity allows us to aggregate policies that produce similar outcomes. This thesis will explore:
- Are policy similarity methods robust to different types changes in the environment?
- Can we enhance these methods with additional contextual information?
Bachelor theses would focus on the first objective, while master theses would tackle both and focus on developing a new method
Contact: Aditya Mohan
-
Reinforcement Learning using Landscape Analysis [M.Sc]
One way to understand how RL algorithms differ is by analyzing the returns obtained by the policy trained by these algorithms. By understanding the distributions of these returns, we can potentially understand aspects about different types of RL algorithms. This thesis will focus on using Landscape Analysis to understand and characterize RL algorithms. The final goal will be to use this characterization for Meta-RL
Contact: Aditya Mohan
-
Augmenting algorithm components in RL through meta-learning [MSc]
We can generate augmentation functions by meta-learning, something for the policy objective in PPO. However, it is open whether this is generally true for algorithm components in reinforcement learning, whether we could also learn augmentation ensembles, and how well these functions generalise. The goal of this work is to extend existing techniques to new algorithms and components.
Contact: Theresa Eimer
-
Enhancing Animal Behavior Analysis via HPO in Object Tracking Algorithms – In Collaboration with Zoo Hannover [MSc]
In collaboration with Zoo Hannover, we aim to enhance object detection and tracking algorithms to monitor the maternal care of Thomson’s gazelles. We integrate Automated Machine Learning (AutoML) and Computer Vision to achieve this, focusing mainly on Hyperparameter Optimization (HPO). The project's primary objective is to improve the analysis of animal behavior using camera data. After identifying leading tracking algorithms, this master's thesis involves an in-depth examination of relevant hyperparameters specific to the corresponding tracking algorithms. The goal of this research is the strategic use of the AutoML tool SMAC to optimize the performance of the tracking algorithms, aiming for enhanced accuracy and efficiency in analyzing animal behavior.
Kontakt: Leona Hennig
Interested?
The exact procedure of a thesis, together with a rough idea of what we expect from theses, is described here.
It is important to us that the appropriate background knowledge is available so that a thesis has a chance of a positive conclusion. In order to be able to assess this accordingly, we would ask you to send us the following points:
Proposed topic or topic area(s)
What previous knowledge is available? What ML-related courses have been taken for this?
- A self-assessment from -- to ++ on the following topics:
- Coding in Python
- Coding with PyTorch
- Ability to implement a Deep Learning paper
- Ability to implement a reinforcement learning paper
- Ability to understand and execute a foreign codebase
If you are generally interested in writing a thesis with us but have not decided on any of the above topics, please email m.lindauer@ai.uni-hannover.de with the above information.
If you are interested in a specific topic indicated above, please send an email directly to the contact person indicated in the topic. The email addresses can be found on the personal pages.
