The mission of AI-vidence is to make AI more explainable. Our conviction is that it is necessary to introduce a component of logical AI (reasoning based on rules) to enable the model to be robust and provide operational guarantees.

The opaque nature of AI models (black-box models derived from machine learning on data) makes their adoption difficult—they are not inherently explainable. However, the European regulation on AI (the AI Act) requires companies to explain their black boxes.

During the summer of 2021, AI-vidence won the tech sprint organized by the ACPR on the topic of explainability. Our ‘regional’ approach to explainability was thus recognized.