About Us

The Department of Machine Learning conducts research and development in both the fundamental aspects of machine learning and other subfields of artificial intelligence, along with their various applications. Our department is structured around two main directions: the first focuses on research teams (an organizational structure that evolves as the group develops), while the second revolves around research projects (where we aim to bring together researchers motivated by a specific research topic, ongoing projects, or grant-funded studies).

Our main research interests and achievements include:

• Machine learning and data mining,
• Neuro-symbolic artificial intelligence and image recognition,
• Trustworthy AI and explainable machine learning models,
• Deep learning for natural language and image processing,
• Modeling of adaptive and complex systems,
• Multi-agent systems: modeling, simulation, and optimization,
• Edge AI systems, quantum generators, and neuromorphic computing with spiking neural networks,
• Heuristic and exact optimization methods.

More details on our research can be found under the Research section in the main menu of this website.

The department is led by prof. dr. hab. inż. Jerzy Stefanowski

Department site

Department employees

Research

The research conducted by department members is related to the following topics:

Machine Learning and Data Mining

• Incremental learning of predictive models from evolving data streams with concept drift,
• Improving classification of imbalanced data,
• Integration of symbolic knowledge and neural networks,
• Application of machine learning and data mining methods in biomedical data, particularly in diagnostic and therapeutic decision support and medical imaging,

Learning from Complex Data

• Online learning of complex knowledge representations from data,
• Complex example representations and structured outputs,
• Text mining and natural language processing.

Trustworthy AI and Explainable Machine Learning

• Research, design, and development of unified methodologies for interpretable machine learning systems, particularly in areas where human-technology interaction is critical,
• New architectures for learning,
• Evaluation criteria for explainable systems,
• Preference modeling and learning preferences from examples,
• Perception and human role consideration in learning systems,
• Automated visualization,
• New interaction methods between AI and humans,
• Responsible AI and fair decision-making.

Other Research Areas

• Process mining – event log analysis for process modeling,
• Exact and heuristic optimization algorithms,
• Spiking neural networks and signal analysis,
• Algorithms for learning spiking neural networks and their applications in edge computing,
• Deep learning in natural language processing,
• Neurosymbolic learning and reasoning,
• Multi-agent systems, evolutionary robotics, biological simulations, and artificial life,
• Neural network topology optimization for real-time control,
• Multicriteria analysis and decision support.