Towards a Conditional and Multi-preferential Approach to Explainability of Neural Network Models in Computational Logic (Extended Abstract)
Contributo in Atti di convegno
Data di Pubblicazione:
2022
Abstract:
This short paper reports on a line of research exploiting a conditional logic of commonsense reasoning to provide a semantic interpretation to neural network models. A “concept-wise" multi-preferential semantics for conditionals is exploited to build a preferential interpretation of a trained neural network starting from its input-output behavior. The approach is a general one; it has first been proposed for Self-Organising Maps (SOMs), and exploited for MultiLayer Perceptrons (MLPs) in the verification of properties of a network by model-checking. An MLPs can be regarded as a (fuzzy) conditional knowledge base (KB), in which the synaptic connections correspond to weighted conditionals. Reasoners for many- valued weighted conditional KBs are under development based on Answer Set solving to deal with entailment and model-checking.
Tipologia CRIS:
04A-Conference paper in volume
Keywords:
Preferential Description Logics, Typicality, Neural Networks, Explainability
Elenco autori:
Alviano M.; Bartoli F.; Botta M.; Esposito R.; Giordano L.; Gliozzi V.; Dupre D.T.
Link alla scheda completa:
Link al Full Text:
Titolo del libro:
Proceedings of the 3rd Italian Workshop on Explainable Artificial Intelligence co-located with 21th International Conference of the Italian Association for Artificial Intelligence(AIxIA 2022)
Pubblicato in: