Machines that learn from large amounts of data can mimic human intelligence to a large degree but are inherently fragile. Our research areas include autonomous vehicles and drones, robots in manufacturing and assisted living, robotic surgery, and AI applications in finance that call for privacy, fairness and ease of use.
This team will work to train people on how to build safe and unbiased algorithms. “While there have been tremendous advances in AI and machine-learning in recent years, these mechanisms are still fragile and opaque,” shared team lead Madhusudan Parthasarathy, Professor of Computer Science. Co-principal investigators on the project are Illinois CS Assistant Professors Sanmi Koyejo and Bo Li.