Enhancing White-Box Machine Learning Processes by Incorporating Semantic Background Knowledge

摘要

Currently, most of white-box machine learning techniques are purely data-driven and ignore prior background and expert knowledge. A lot of this knowledge has already been captured in domain models, i.e. ontologies, using Semantic Web technologies. The goal of this research proposal is to enhance the predictive performance and required training time of white-box models by incorporating the vast amount of available knowledge in the pre-processing, feature extraction and selection phase of a machine learning process.