Radiology take note: Facebook gets superfast with AI vision training

Researchers at Facebook—you read those three words right—have developed a way to feed image data to AI visual-recognition models at a much faster pace than ever before, and with no compromise on precision. Radiology AI developers are sure to watch and learn.

The social-media behemoth says its new system can train the models at a blazing 40,000 images per second. 

This means machine-vision training that typically takes days if not weeks can now be done in less than an hour, according to a 1-minute read in Fast Company.

“From digital camera tools aimed at consumers and advanced medical screening to helping develop autonomous cars and much more,” the writer adds, “this development could speed up R&D and make things easier for many people and companies.”

Read the rest: 

Dave Pearson

Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.

Trimed Popup
Trimed Popup