This didn’t occur since the robot was programmed to do harm. It was since the robot was overly confident that the boy’s finger was a chess piece.  

The incident is a classic example of something Sharon Li, 32, wants to stop. Li, an assistant professor on the University of Wisconsin, Madison, is a pioneer in an AI safety feature called out-of-distribution (OOD) detection. This feature, she says, helps AI models determine after they should abstain from motion if faced with something they weren’t trained on. 

Li developed certainly one of the primary algorithms on out-of-distribution detection for deep neural networks. Google has since arrange a dedicated team to integrate OOD detection into its products. Last yr, Li’s theoretical evaluation of OOD detection was chosen from over 10,000 submissions as an impressive paper by NeurIPS, one of the crucial prestigious AI conferences.

We’re currently in an AI gold rush, and tech firms are racing to release their AI models. But most of today’s models are trained to discover specific things and sometimes fail after they encounter the unfamiliar scenarios typical of the messy, unpredictable real world. Their inability to reliably understand what they “know” and what they don’t “know” is the weakness behind many AI disasters. 

Li’s work calls on the AI community to rethink its approach to training. “Plenty of the classic approaches which have been in place over the past 50 years are literally safety unaware,” she says. 

Her approach embraces uncertainty through the use of machine learning to detect unknown data out on the earth and design AI models to regulate to it on the fly. Out-of-distribution detection could help prevent accidents when autonomous cars run into unfamiliar objects on the road, or make medical AI systems more useful find a latest disease.