Fysikkbygningen øst (kart)
Sem Sælands vei 24
In this thesis, you will investigate how modern structure-aware machine learning techniques can be applied to practical challenges usually approached using classic symbolic AI techniques. Specifically, you will develop novel algorithms based on graph neural networks (GNNs) for anomaly detection in knowledge graphs, and test them against existing approaches in synthetic and real-life settings.
Knowledge Graphs have emerged as a paradigm for representing data and semantics, providing new possibilities for a wide variety of data-driven tasks (e.g., data integration, data analytics, search, query answering, entity disambiguation, etc.). Driven by a new generation of Web and enterprise applications, advances in NoSQL graph databases, as well as the need for enhanced learning, the technology behind Knowledge Graphs is now maturing to a level that has become practical in various domains. The aim of this thesis is to study the applicability of Knowledge Graphs in the area of (network) neuroscience for modeling and analyzing how the brain works. More specifically, the thesis will cover design of Knowledge Graphs for modelling physical pathways that build functional networks from which cognitive capacities emerge, generation and storage of data in such Knowledge Graphs, as well as analytics on the data. The aim is to test the suitability of the Knowledge Graphs paradigm in helping to understand how the brain works.
Related relevant background article can be found here.
The types of MSc theses that I could offer fall within three categories: