TU Berlin

Neural Information ProcessingTheses Projects (Bachelor & Master)

Neuronale Informationsverarbeitung

Page Content

to Navigation

Bachelor and Master Theses

Thank you for your interest in writing your bachelor or master thesis in the field of neural information processing. The focus of possible thesis projects will be closely linked to ongoing research projects of our group. Below you can find open thesis projects and the corresponding contact persons.  If the topic you are interested in is not listed, please contact .

Potentielle Themen

Safe Reinforcement learning

Exploring Biologically inspired features for sound event detection in difficult Polyphonic acoustic scenes

Exploring Blind source separation for Sound Event Detection in Moving  Acoustic scenes

Understanding Semantic Segmentation of Sound Events in Binaural Auditory Scenes

Semi-Supervised and Data Augmentation Schemes for Polyphonic Sound event detection in Reverberant  Binaural auditory scenes

Training Neural Networks with evolutionary methods instead of back propagation (MSc)
The standard way for training Neural Networks (NN) is by calculating the gradient of the NN function with respect to the weights/parameters and move along its direction. This method is dominant, mainly due to the fact that the gradient is computationally cheap to calculate. However alternative methods exist. One of this method is the evolutionary approach or gradient free optimization (depending on the community). In this method, one randomly samples various points around the current value of the parameters, and picks a weighted mean of this points as the new point. The advantage of this approach is that it can escape local minima, and that can be applied to cases where the error functions are not differentiable. The goal of the student is to compare these methods in various toy problems.

Comparing different approaches for creating templates out of brain MRIs (MSc)
In MRI studies, it is common to create various templates out of the different groups, before one makes the analysis. These templates are some form of averages, which can be used either as a baseline, or as the objects to be compared between groups. The last decade, a method for calculating averages of images has been developed using either the Wasserstein or the Hellinger-Kantorovich distance. Therefore this method can also be applied for MRIs to create templates. The purpose of this thesis is the comparison of traditional methods for creating templates with these newer approaches.

Training Neural networks that capture the Wasserstein and Hellinger-Kantorovich
distance (MSc)

The purpose of this project is the training of Neural networks that capture the Wasserstein Metric for a specific dataset (MRI or MNIST images). The NNs will be then analyzed and possibly applied to other projects.

Computational modeling of separable resonant circuits controlled by different interneuron types
(Computational Neuroscience, Biophysically Detailed Modeling)

The influence of cell-intrinsic alterations in schizophrenia on oscillatory behaviour in cortical neural networks
(Computational Neuroscience, Computational Psychiatry, Spiking Neural Networks&Mean-Field Modeling)

Automated validation and comparison of models of neurophysiological and neurocognitive biomarkers of psychiatric disorders
(Computational Neuroscience, Computational Psychiatry, Neuroinformatics)

Modelling Resting-State MEG Dynamics in Health and Disease
(Connectomics, Neuropsychiatric Disorder, Network Science, Computational Psychiatry)

Mechanistic Models of Excitatory-Inhibitory Interactions in the Auditory Cortex in Schizophrenia
(Neuropsychiatric Disorder, Computational Neuroscience, Computational Psychiatry)

Risk-sensitive deep reinforcement learning

Something related to meta-learning, transfer learning and "towards understanding of neural networks". (Please write me if you are interested)


Quick Access

Schnellnavigation zur Seite über Nummerneingabe