A new AI identifies objects at the speed of light — Here's what that means for healthcare

A team of electrical and computer engineers from UC Los Angeles developed an artificial intelligence device that identifies objects at the speed of light, the university announced Aug. 2.

Using a 3D printer, the engineers created a physical artificial neural network composed of a series of polymer layers. Each layer — an eight-centimeter square — comprises tens of thousands of artificial neurons that analyze the way light bounces from an object to identify what the object is.

The engineers trained the device using deep learning, a type of AI modeled on how the human brain processes information. In deep learning, a machine learns over time by extracting patterns from data.

In a study published in Science, the engineers demonstrated how the device accurately identified handwritten numbers and items of clothing. Although the device is still in development, the engineers suggested it could be applied to data-intensive fields like medicine, robotics and security. For example, technology based on the invention could be used to help microscopic imaging devices sort through millions of cells for signs of disease.

"This work opens up fundamentally new opportunities to use an artificial intelligence-based passive device to instantaneously analyze data, images and classify objects," Aydogan Ozcan, PhD, an electrical and computer engineering professor at UCLA and principal investigator on the study, said in a news release.

More articles on artificial intelligence:
Nuance adds Mark Sherwood as CIO: 4 things to know
Harvard, UPenn researchers use AI to predict mortality for cancer patients
12 healthcare use cases for natural language processing

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Webinars

Featured Whitepapers