![Flower close-up](https://safe-intelligence.fraunhofer.de/transforms/images/articles/2023-04-17-concept-based-models-how-visual-concepts-help-to-understand-an-ais-decision/_360x540_crop_center-center_90_none/blueten-close-up.jpg)
Concept-based Models
How visual concepts help to understand an AI’s decision
Modern AI models have demonstrated remarkable capabilities on various computer vision tasks such as image classification. Their decision-making process, though, remains mostly opaque (black box problem). This can be particularly problematic for safety-critical applications like medical imaging or autonomous driving. Fraunhofer IKS explores ways to increase the transparency of this black box.