Interpretable ensembles of local models for safety-related applications

This paper discusses a machine learning approach for bi- nary classification problems which satisfies the specific requirements of safety-related applications. The approach is based on ensembles of local models. Each local model utilizes only a small subspace of the complete input space. This ensures the interpretability and verifiability of the local models, which is a crucial prerequisite for applications in safety-related domains. A feature construction method based on a multi-layer percep- tron architecture is proposed to overcome limitations of the local modeling strategy, while keeping the global model interpretable.