I currently work at forml on software for administration processes in government.

Important Courses:

• Reinforcement Learning
• Scalable Artificial Intelligence
• Research Project on Technical Privacy and Explainable Artificial Intelligence
• Security
• Resilient Networking
• Probability Theory
• Statistics

Final Grade: 1.0

“Utility of Semantic Privacy Notions for Correlated Data”

• Establishes theoretical relationship between the privacy notions differential privacy and Bayesian differential privacy
• Involves mathematical proofs when assuming different probability distributions of the underlying data (multivariate normal distribution, Markov chain, genomic data)
• Experiments implemented in Python

Applying machine learning to automatically categorize and analyze textual customer feedback.

• Training LSTMs in Python to classify customer feedback into categories.
• Developing a process to evaluate the performance of NLP models with confidence intervals through bootstrapping.
• Developing a process to continuously evaluate production NLP models by estimating the distribution of positive classifications in the embedding space and detecting distributional drift.
• Analyzing trends in customer feedback via SQL queries for a monthly report.
• Conducting interviews with customers concerning new product launches.

Student tutor for third-year computer science students in subject “programming paradigms”. The lecture comprises parallel programming, basics of compiler construction, functional programming (Haskell), logic programming (Prolog), lambda calculus, and type inference.

Student assistant working on research on explainable artificial intelligence such as SHAP and LIME by examining their effect on data privacy.

Important Courses:

• Cognitive Systems
• Machine Learning – Basic Methods
• Laboratory for Applied Machine Learning Algorithms

Final Grade: “with distinction” (1.2)