MAS Emergence Safety
Formalized MAS emergence misalignment; proposed safety mitigation strategies.
Machine Learning Researcher and Data Science Expert with a PhD in Computer Science. Brings 6+ years of experience developing and analyzing algorithms, models and foundational research, evidenced by numerous publications. Proven ability to translate complex technical concepts into practical solutions and communicate effectively with diverse stakeholders. Loves to offer expertise in AI/ML (PyTorch), data science, and problem-solving to drive impactful results.
This portfolio offers a detailed overview of my academic background, professional journey, research contributions, and technical expertise.
Explore the sections detailing my research, teaching experience, key projects, and publications to gain deeper insights into my work. You can navigate through the site using the top menu for detailed information on specific areas.
Formalized MAS emergence misalignment; proposed safety mitigation strategies.
Aquarium: Open-source MARL environment for predator-prey studies.
Managed LMU chair IT: Kubernetes, CI/CD, automation (2018-2023).
Binary subsegment presorting improves noisy primate sound classification.
Artificial chemistry networks develop predictive models via surprise minimization.
LSTM autoencoder better DP for trajectory compression (Fréchet/DTW).
VoronoiPatches improves CNN robustness via non-linear recombination augmentation.
Self-replicating networks collaborate forming higher-level Organism Networks with emergent functionalities.