Machine Learning Scientist / Data Analyst / Software Developer

8/2019 – 2/2020

Development of an android app combining computer vision and machine learning. Detection of faces from camera and image input, comparison to database entries (CelebA Dataset) for face matching.
Languages: Java
Tools and libraries: Android Studio, Java-ML, deeplearning4j

Computer Vision, Maschinelles Lernen, Android

5/2019 – 11/2019

Research Scientist in the group of Secure Information Technology of the Technical University Darmstadt/ Fraunhofer SIT at the department Cybersecurity Analytics and Defences.
- Researched state-of-the-art methods in cybersecurity, especially in using machine learning models for intrusion detection and prevention, as well as for automated firewall configurations
- Management of funding for interns and assistants
- Held job interviews for new tutors in the department
- Organization of the lectures: worked as a lecturer, designed and corrected exams, helped with exercise classes
- Participated in weekly reading groups and presented project results

Cyber Security, Maschinelles Lernen

3/2019 – 4/2019

Full-stack development of an automated billing software running on both windows and macOS machines. The software was connected to a database using mySQL and phpmyadmin. UI design and implementation. Amortization of the software.
Languages: Java
Tools and libraries: PDFBox, JODConverter, Apache POI, phpMyAdmin, mySQL, com.spire.doc, JFreeChart

Apple Mac Systems, Microsoft Windows (allg.), Java (allg.)

1/2018 – 1/2019

Convolutional neural networks have seen a rise in the computer vision community in the recent years, even surpassing human accuracies in face recognition tasks.

However, research regarding different face classification and face clustering experiments, which do not focus on the discrimination of face images according to unique individuals in the dataset, are still very limited. Many psychological studies indicate that humans are capable in inferring leaders, status and competence from facial images. This work focused on the question whether humans are indeed capable in telling profession – given by the branch of the profession and the career status – from face images and whether current state-of-the-art machine learning approaches
are able to do the same.

Furthermore, the performance of humans and machine learning systems were compared to give insights in the underlying processes.

Computer Vision, Deeplearning4j, Faltendes Neuronales Netzwerk (CNN), Keras, Maschinelles Lernen, Neuronale Netze, Pandas, Pytorch, Support Vector Machine, Tensorflow, Python

7/2015 – 9/2015

Implementation of state-of-the-art deep learning models to predict down-regulation of amygdala activation from resting-state functional connectivity (fMRI data). First and second level statistical analysis. ROI and multiple regression analysis.
Languages: Python, R, Matlab
Tools and libraries: Matlab SPM8, CONN, Tensorflow

Tensorflow, SAP SPM, Simulink, Python

1/2015 – 1/2016

Internship at the Central Institute for Mental Health in the department of Neuroimaging
- Processing psychophysical and neuropsychological experiments
- Screenings for proband acquisition and administration of proband lists in Excel and SPSS
- Programming experimental environments with C++, Python, OpenSesame and Presentation
- Processing and evaluating fMRI data with R, Matlab, FSL and SPM

SAP SPM, C++, Simulink, Python