Computer scientists just developed a system for helping AI understand human goals
Artificial intelligence systems are opaque, especially to people without a relevant technical background and enough time to dig into the code.
But it doesn't have to be that way.
That's why teams of researchers worldwide are racing to develop AI systems that can communicate with their human operators in a language they can understand. One of those teams has just made a big step forward. In a paper published on July 13th in the peer-reviewed journal Science Robotics, a team of researchers from the U.S. and China presents a framework for what they call "explainable artificial intelligence," or XAI.
Subscribe today for full access to all features and product updates.
- Unlimited access to IE+ with exclusive features, interviews and analysis
- Commenting feature with our high-quality engineering community
- Audio articles, exclusively for premium users
- A weekly premium newsletter that goes beyond the headlines
- Ad-free experience
- Future benefits still to come