- Thursday 21 January; 15:30: ELEC Seminar by Gaia Cavallo
Focus on this set of Master theses
Our knowledge society generates vast amounts of data (audio, photo’s, video’s), new knowledge and technologies. Processing the data is nowadays often automated using artificial intelligence techniques. However, the optimal usage of all the new knowledge/technologies by the next generations will require that the learning rate, i.e. the rate to pass the knowledge from generation to generation, must increase.
These master theses proposal aims to take the first fundamental steps to increase up the learning rate.
- Model and import the knowledge to be learned using a knowledge graph representation.
- Measure the learning rate of by the student using the knowledge graph representation, i.e. the transfer rate of the knowledge graph of the domain towards the “graph” in the student’s brain. This measurement is not straightforward as different levels of understand of the knowledge must be considered, i.e. remembering, using, comparing, inventing, ….
The implementations are preferably done in Python, while the data is stored in a graph database such as neo4j.