UVT – ExplainableAI Reading Group Meeting – April 2026 Edition

On April 27, 2026, the UVT – ExplainableAI Reading Group meeting took place.

The focus of this edition was from local to global explanations with propositional rules.

The special guest was Prof. Dr. Guido Bologna, University of Applied Sciences and Arts of Western Switzerland. Deep connectionist models are characterized by many neurons grouped together in many successive layers. As a result, their data classifications are difficult to understand. This talk presented two algorithms which explain the responses of several black-box machine learning models. The first is Fidex, which is local and thus applied to a single sample. The second, called FidexGlo, is global and uses Fidex