'Periodic table' for AI methods aims to drive innovation

Eslam Abdelaleem led the work as an Emory graduate student. The day of the final breakthrough, the AI health tracker on his watch recorded his racing heart as three hours of cycling. "That's how it interpretated the level of excitement I was feeling," Abdelaleem says. (Photo by Barbara Conner)

Artificial intelligence is increasingly used to integrate and analyze multiple types of data formats, such as text, images, audio and video. One challenge slowing advances in multimodal AI, however, is the process of choosing the algorithmic method best aligned to the specific task an AI system needs to perform. 

Scientists have developed a unified view of AI methods aimed at systemizing this process. The Journal of Machine Learning Research published the new framework for deriving algorithms, developed by physicists at Emory University. 

“We found that many of today’s most successful AI methods boil down to a single, simple idea — compress multiple kinds of data just enough to keep the pieces that truly predict what you need,” says Ilya Nemenman, Emory professor of physics and senior author of the paper. “This gives us a kind of ‘periodic table’ of AI methods. Different methods fall into different cells, based on which information a method’s loss function retains or discards.”

Read the full story here.