As AI models are released into the wild, this innovator wants to ensure they’re safe


This did not happen because the robot was programmed to do harm. It was because 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 prevent. Li, an assistant professor at 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 when they should abstain from action if faced with something they weren’t trained on. 

Li developed one of the first algorithms on out-of-distribution detection for deep neural networks. Google has since set up a dedicated team to integrate OOD detection into its products. Last year, Li’s theoretical analysis of OOD detection was chosen from over 10,000 submissions as an outstanding paper by NeurIPS, one of the most prestigious AI conferences.

We’re currently in an AI gold rush, and tech companies are racing to release their AI models. But most of today’s models are trained to identify specific things and often fail when 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. 

SARA STATHAS

Li’s work calls on the AI community to rethink its approach to training. “A lot of the classic approaches that have been in place over the last 50 years are actually safety unaware,” she says. 

Her approach embraces uncertainty by using machine learning to detect unknown data out in the world and design AI models to adjust 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 in finding a new disease. 

Leave a Reply

Your email address will not be published. Required fields are marked *

8 Times Amy Jackson Took The Internet By Storm With Her Glamorous Avatar February 14, 2024 Here Are Best Anime Couples Of All Time – Koimoi Keerthy Suresh Exudes Elegance In A Timeless Yellow Saree February 1, 2024 Madhuri Dixit Steals Hearts In A Blue Saree February 3, 2024 8 Unknown Facts About Controversial Actress-model Poonam Pandey February 5, 2024 Sruthi Haasan Raises Glam Quotient In A Green Printed Co-ord Set February 5, 2024 8 Times Kriti Sanon Made Heads Turn In Stylish Outfits February 6, 2024 Alaya F Looks Smoking Hot In Silver Bodycon Dress February 7, 2024 Janhvi Kapoor Turns Heads In A Ravishing Red Dress February 8, 2024 Priyamani Looks Every Bit Of An Ethnic Diva In Royal Blue Striped Silk Saree February 9, 2024 Deepti Sati's Glamorous Lehenga Looks February 10, 2024 Netflix’s Global Top 10 Films: From Lift To The Super Mario Bros Movie, See The Full List! – Koimoi Must Watch Top 10 Anime High School Romcoms – Koimoi What To Watch On HBO And Max In February 2024 – Koimoi Top 7 Grinch Movies And TV Shows To Watch This Christmas Season – Complete Details Inside! – Koimoi Complete Guide To Watch Every Godzilla Movie In The Monsterverse — With Release And Chronological Order – Koimoi Top 5 Underrated Horror Anime Series – Koimoi Best Shoujo Romance Anime of All Time — You’re Not Ready for These – Koimoi Highest-Grossing Anime Movies: From Your Name, Demon Slayer & The First Slam Dunk – Films That Managed To Redefine Animated Cinema! – Koimoi 5 Best Black Anime Characters In Most Impactful And Trailblazing Anime – Koimoi