research

Here you’ll find a curated overview of the papers where I have played a pivotal role, either as the first author or as a contributing author further down the authorship line. My involvement has spanned a variety of activities, from conceptualizing the initial ideas and developing machine learning models, to providing support and insights to my colleagues, or rigorously reviewing and refining the work.

List of Papers

Binary Presorting

Improving Primate Sounds Classification

Social NN-Soup

Social interaction based on surprise minimization

Voronoi Patches

Evaluating A New Data Augmentation Method

Organism Networks

Constructing ON from Collaborative Self-Replicators

Self-Replication in NNs

Elaboration and journal article of the initial paper

Anomaly Detection in RL

Towards Anomaly Detection in Reinforcement Learning

Self-Replication Goals

Combining replication and auxiliary task for neural networks.

Mel-Vision Transformer

Attention based audio classification on Mel-Spektrograms

Primate Vocalization Classification

A Deep and Recurrent Architecture

Acoustic Leak Detection

Anomalie based Leak Detection in Water Networks

Anomalous Image Transfer

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Anomalous Sound Detection

Analysis of Feature Representations for Anomalous Sound Detection

Surgical Mask Detection

Convolutional Neural Networks and Data Augmentations on Spectrograms

What to do in the Meantime

Service Coverage Analysis for Parked Autonomous Vehicles

Policy Entropy for OOD Classification

PEOC for reliably detecting unencountered states in deep RL

Point Cloud Segmentation

Segmetation of point clouds into primitive building blocks.

Learning Soccer-Team Vecors

Team market value estimation, similarity search and rankings.

Deep-Neural Baseline

Introduction a deep baseline for audio classification.

Self-Replication in Neural Networks

Introduction of NNs that are able to replicate their own weights.

Trajectory annotation by spatial perception

We propose an approach to annotate trajectories using sequences of spatial perception.