• clustering methods
• information theory
• entropy based classification

• hierarchical classification
• deep learning
• learning theory

• software testing and quality
• automata and formal languages
• classification theory

• urban mobility and transport systems
• social systems
• network science
• agent-based models

• generative models
• continual learning

• compression theory
• clustering methods

• clustering methods
• entropy theory
• semi-supervised learning

• computer vision
• machine learning
• representation learning

• computer vision
• explainable artificial intelligence
• deep learning

• information theory
• machine learning
• bioinformatics
• algorithm complexity
• graph theory
• physics

• AI in urban transport
• Reinforcement learning
• Mathematical analysis and modelling

• image processing
• biometrics methods

• machine learning
• deep learning

• computer-aided drug design
• pharmacoinformatics
• geometric deep learning

• deep learning
• hyperspectral imaging
• continual learning
• biomedical applications of machine learning

• deep learning
• natural language processing
• representation learning

Supervisor: Prof. Jacek Tabor

• independent component analysis
• compression algorithms

Supervisor: Prof. Jacek Tabor

• computer vision
• biomedical imaging
• interpretability

Supervisor: Prof. Jacek Tabor

• computer vision
• generative models
• autoencoders

Supervisor: Prof. Marcin Mazur

• network science
• probability theory
• complex systems

Supervisor: Prof. Rafał Kucharski

• deep metric learning
• object detection
• ML in medical imaging
• natural language processing

Supervisor: Prof. Krzysztof Geras

• molecular property prediction

Supervisor: Prof. Marek Śmieja

• urban mobility and transport systems
• complex adaptive systems
• agent-based modeling

Supervisor: Prof. Rafał Kucharski

• generative models
• 2D and 3D computer vision
• graph neural networks

Supervisor: Prof. Przemysław Spurek

• continual learning
• natural language processing
• reinforcement learning

Supervisor: Prof. Przemysław Spurek

• cheminformatics
• graph convolutional neural networks
• natural language processing

Supervisor: Prof. Jacek Tabor

• computer vision
• interpretable neural networks
• open world setting

Supervisor: Prof. Bartosz Zieliński

• disentanglement learning
• neural architecture search

Supervisor: Prof. Jacek Tabor

• computer vision
• efficient Machine Learning
• multimodal learning

Supervisor: Prof. Bartosz Zieliński

• computer vision
• partial information
• interpretability

Supervisor: Prof. Bartosz Zieliński

• natural language processing
• sequence-to-sequence models

Supervisor: Prof. Jacek Tabor

• meta-learning
• self-supervised learning
• computer vision

Supervisor: Prof. Marek Śmieja

• optimization
• generative models
• bayesian machine learning

Supervisor: Prof. Tomasz Trzciński

• computer vision
• medical imaging
• active learning
• interpretability of neural networks

Supervisor: Prof. Jacek Tabor

• deep learning for drug discovery
• few-shot learning
• generative models

Supervisor: Prof. Jacek Tabor

• computer vision
• generative models
• visual reasoning

Supervisor: Prof. Jacek Tabor

• meta-learning & continual learning
• few-shot learning
• deep generative models

Supervisor: Prof. Jacek Tabor

• generative models
• reinforcement learning

Supervisor: Prof. Igor T. Podolak

• natural language processing
• theory of programming languages

Supervisor: Prof. Jacek Tabor

• representation learning
• personalized NLP
• graph neural networks

Supervisor: Prof. Przemysław Spurek

• continual learning
• conditional computation
• reinforcement learning

Supervisor: Prof. Jacek Tabor

• dynamic networks
• uncertainty
• adversarial examples

Supervisor: Prof. Marek Śmieja

• deep learning
• cheminformatics

Supervisor: Prof. Jacek Tabor

• representation learning
• bioinformatics (metagenomics)
• natural language processing
• tabular learning

Supervisor: Prof. Marek Śmieja

• continual learning
• reinforcement learning

Supervisor: Prof. Piotr Miłoś