Alex Bäuerle, M. Sc.
I completed my masters degree at the Institute of Media Informatics 2017 before joining the research group Visual Computing. Since then, I work on visualization in the domain of artificial intelligence.
- Neural network visualization
- Visualization of training data
- Visualization of classification results
I supervise(d) the following lectures:
Theses and Projects
I would gladly supervise theses from the field of neural networks. I am especially interested in generating visualizations of networks, training results and training data. We can, however, also discuss other topics in the field of neural Networks via mail or in my office.
Important: The selection of projects that can be found below is only a subset of possibilities. Working on your own ideas is always possible. Also, most of the time, I have some additional projects ready to be tackled. Therefore, it's always worth making a personal appointment.
Analyzing fibril structures is important for biochemnists to better understand the human body and investigate possible reasons for certain deseases. After fibrils have been scanned using micro-ct, the researchers analyze their chemical composition and reconstruct their threedimensional shape.
This reconstruction is currently done using some parameters that can be extracted from the scans. Then, a reconstruction program tries to simulate the geometry of the fibril. Toj do this, one needs some preprocessing steps. In this work, the reconstruction process should be replaced with a neural network, to automate and possibly improve the reconstruction.
Neural networks have evolved a lot over time. There have been different architectures used over time and new problems and techniques have emerged. Comparing these is a tedious task, especially when not trained on the same dataset.
This work should give a historic overview of the development of these Networks and make comparing them possible. The interactive visualization should respect different properties of the network and make them easily comparable. It should be publicly accessible and thus web-based.
PointNets are used to train neural networks on pointclouds. While there are many visualization techniques for image-based neural networks, PointNets are lacking such visualizations.
This work aims at providing such visualizations for PointNets. It includes reading up on existing visualization techniques for ImageNets, but should also contain the elaboration of new visualization options for these types of networks.
This masters thesis is done in cooperation with the Center for Translational Imaging. During transcatheter aortic valve implantations, the patient is observed using imaging technology.
Ofthen, doctors use overlays of important organs to help them during surgery. Since the patient is breathing during the whole process, this placement is often inaccurate.
To tackle this problem, a neural network is trained that recognizes the movement induced by the breath of the patient. This helps us to reposition the overlay used during the treatments.
In cooperation with the Institute of Protein
Biochemnistry, this project was aimed to automatically detect crossovers in micro-ct scans of fibrils. These crossovers are important for analyzing and reconstructing the scanned fibrils.
To enable this automatic localization of crossovers, a neural network for semantic segmentation of fibril images was trained as a student project.