Projects

Research Interests

Resource-efficient deep learning for real-time applications

Optimization of deep learning models for use in resource-constrained environments with real-time requirements.

This research direction focuses on the development and optimization of deep learning architectures that can operate efficiently on resource-constrained systems. The goal is to create innovative solutions that enable complex AI models on devices with limited computing power.

Agentic systems for industry and education

Development and application of intelligent agents for practical solutions in industrial and educational contexts.

This research area deals with the design and implementation of agent-based systems that can handle complex tasks in real-world environments. The focus is on the development of agents that can be used in industrial scenarios (e.g. autonomous robots for manufacturing processes or self-driving vehicles) as well as in educational contexts (e.g. interactive learning environments with AI-controlled components).

Explainable AI for improved human-machine interaction

Research and application of explainable AI (XAI) methods to improve the transparency and comprehensibility of AI systems in technical applications.

This research direction aims to make the decision-making processes of AI systems more transparent and comprehensible, especially in contexts where there is close interaction between humans and machines. The aim is to research and apply techniques for visualizing AI decisions, generating comprehensible explanations and developing intuitive interfaces for interacting with AI systems.