Information fusion
Investigation of methods for integrating information from multiple sources or modalities, with emphasis on joint representations, consistency across sources, uncertainty management, and principled evidence combination in inference.
Explainability
Analysis of explainability as a formal property of AI models, including the study of explanatory mechanisms, their expressiveness and limitations, and their relationship to model complexity and predictive performance.
Computational neuroscience
Development and analysis of computational models inspired by neural systems, aimed at understanding information-processing mechanisms and informing the design of learning algorithms and architectures grounded in neurocomputational principles.
Quantum communication and AI
Study of the interaction between artificial intelligence and quantum communication and computation, addressing both the use of quantum principles in learning and optimization and the application of AI techniques to the control and operation of quantum systems.
Multimodal learning
Research on learning models that integrate information from multiple modalities, focusing on the theoretical foundations of alignment, shared representation, and information transfer across heterogeneous data types.
Learning theory
Formal study of machine learning processes, including generalization properties, model complexity, theoretical limits of learnability, and conditions for stability and convergence.
