KAIST XAI Tutorial 2024 | Model Behavior with Concept-based Explanations | M.Dreyer (Fraunhofer HHI)

Concept-based explanations offer deep insights into neural networks, but analyzing individual explanations across large datasets can be inefficient. In this talk, we solve this by summarizing similar explanations with prototypes, providing a quick yet detailed overview of the model behavior. This approach is promising for monitoring model strategies while learning and allows to quickly spot model weaknesses. Prototypes further help to validate newly seen predictions by comparing them to prototypes, making it easier to identify outliers or assign predictions to known model strategies.