Menu
Researchers enable computers to teach themselves common sense

Researchers enable computers to teach themselves common sense

By studying millions of images, a computers at Carnegie Mellon are getting smarter

While some people may think they're getting dumbed down as they scroll through images of cats playing the piano or dogs playing in the snow, one computer is doing the same and getting smarter and smarter.

A computer cluster running the so-called the Never Ending Image Learner at Carnegie Mellon University runs 24 hours a day, 7 days a week searching the Internet for images, studying them on its own and building a visual database. The process, scientists say, is giving the computer an increasing amount of common sense.

"Images are the best way to learn visual properties," said Abhinav Gupta, assistant research professor in Carnegie Mellon's Robotics Institute. "Images also include a lot of common sense information about the world. People learn this by themselves and, with [this program], we hope that computers will do so as well."

The computers have been running the program since late July, analyzing some three million images. The system has identified 1,500 types of objects in half a million images and 1,200 types of scenes in hundreds of thousands of images, according to the university.

The program has connected the dots to learn 2,500 associations from thousands of instances.

Thanks to advances in computer vision that enable software to identify and label objects found in images and recognize colors, materials and positioning, the Carnegie Mellon cluster is better understanding the visual world with each image it analyzes.

The program also is set up to enable a computer to make common sense associations, like buildings are vertical instead of lying on their sides, people eat food, and cars are found on roads. All the things that people take for granted, the computers now are learning without being told.

"People don't always know how or what to teach computers," said Abhinav Shrivastava, a robotics Ph.D. student at CMU and a lead researcher on the program. "But humans are good at telling computers when they are wrong."

He noted, for instance, that a human might need to tell the computer that pink isn't just the name of a singer but also is the name of a color.

While previous computer scientists have tried to "teach" computers about different real-world associations, compiling structured data for them, the job has always been far too vast to tackle successfully. CMU noted that Facebook alone has more than 200 billion images.

The only way for computers to scan enough images to understand the visual world is to let them do it on their own.

"What we have learned in the last five to 10 years of computer vision research is that the more data you have, the better computer vision becomes," Gupta said.

CMU's computer learning program is supported by Google and the Office of Naval Research.

Sharon Gaudin covers the Internet and Web 2.0, emerging technologies, and desktop and laptop chips for Computerworld. Follow Sharon on Twitter at @sgaudin, or subscribe to Sharon's RSS feed . Her email address is sgaudin@computerworld.com.

Read more about emerging technologies in Computerworld's Emerging Technologies Topic Center.


Follow Us

Join the New Zealand Reseller News newsletter!

Error: Please check your email address.

Tags hardwareserversEmerging Technologieshardware systems

Featured

Slideshows

Sizing up the NZ security spectrum - Where's the channel sweet spot?

Sizing up the NZ security spectrum - Where's the channel sweet spot?

From new extortion schemes, outside threats and rising cyber attacks, the art of securing the enterprise has seldom been so complex or challenging. With distance no longer a viable defence, Kiwi businesses are fighting to stay ahead of the security curve. In total, 28 per cent of local businesses faced a cyber attack last year, with the number in New Zealand set to rise in 2017. Yet amidst the sensationalism, media headlines and ongoing high profile breaches, confusion floods the channel, as partners seek strategic methods to combat rising sophistication from attackers. In sizing up the security spectrum, this Reseller News roundtable - in association with F5 Networks, Kaspersky Lab, Tech Data, Sophos and SonicWall - assessed where the channel sweet spot is within the New Zealand channel. Photos by Maria Stefina.

Sizing up the NZ security spectrum - Where's the channel sweet spot?
Kiwi channel comes together for another round of After Hours

Kiwi channel comes together for another round of After Hours

The channel came together for another round of After Hours, with a bumper crowd of distributors, vendors and partners descending on The Jefferson in Auckland. Photos by Maria Stefina.​

Kiwi channel comes together for another round of After Hours
Consegna comes to town with AWS cloud offerings launch in Auckland

Consegna comes to town with AWS cloud offerings launch in Auckland

Emerging start-up Consegna has officially launched its cloud offerings in the New Zealand market, through a kick-off event held at Seafarers Building in Auckland.​ Founded in June 2016, the Auckland-based business is backed by AWS and supported by a global team of cloud specialists, leveraging global managed services partnerships with Rackspace locally.

Consegna comes to town with AWS cloud offerings launch in Auckland
Show Comments