TY  - CONF
T1  - Explanation of Deep Learning Models via Logic Rules Enhanced by Embeddings Analysis, and Probabilistic Models
A1  - Contreras, Victor H.
A1  - Schumacher, Michael
A1  - Calvaresi, Davide
TI  - Post-proceedings of the 6th International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems
Y1  - 2024
KW  - Deep Learning
KW  - Heterogeneous data processing
KW  - Preference modeling
KW  - rule extraction
KW  - Uncertainty reasoning
KW  - XAI
N2  - 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 uncer- tainty inherent to the data. To this end, this study proposes a pipeline to explain heterogeneous data-based DL models by combining embed- ding 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) integra- tion of textual data into the explanation pipeline through embedding analysis.
ER  -