Explainable Data-Centric AI

Explore the concept of Data-Centric AI (DCAI) in this 31-minute talk from the Alan Turing Institute's AIM RSF Open Invitation seminar series. Delve into the iterative, human-in-the-loop process involving complex patterns of data selection, engineering, and curation, as well as model training, testing, deployment, and monitoring. Discover how systematically recording end-to-end, data-to-AI patterns in detail is crucial for achieving explainability, reproducibility, accountability, and sustainability in AI systems. Learn about the next generation of robust, fair, and responsible AI systems with sustainable performance. Access accompanying slides for a comprehensive understanding of the topic.