Hybrid AI architecture could turn neuromorphic systems into reliable discovery machines

The artificial intelligence (AI) machines that guide the world can be grouped into three main categories: inference machines, learning machines and discovery machines. Researchers at Washington University in St. Louis are tackling the rarest of these machines. A new study points to a better way to build discovery machines, thanks to recent research led by Shantanu Chakrabartty, the Clifford W. Murphy Professor and vice dean for research in the McKelvey School of Engineering at Washington University in St. Louis.