Explanation of Deep Learning Models via Logic Rules Enhanced by Embeddings Analysis, and Probabilistic Models

Deep Learning (DL) models are increasingly dealing with heterogeneous data (i.e., a mix of structured and unstructured data), calling for adequate eXplainable Artificial Intelligence (XAI) methods. Nevertheless, only some of the existing techniques consider the uncertainty inherent to the data. To this end, this study proposes a pipeline to explain heterogeneous data-based DL models by combining embedding analysis, rule extraction methods, and probabilistic models. The proposed pipeline has been tested using synthetic data (multi-individual food items tracking). This study has achieved (i) inference enhancement through probabilistic and evidential reasoning, (ii) generation of logical explanations based on extracted rules and predictions, and (iii) integration of textual data into the explanation pipeline through embedding analysis.