New research aims to teach computers common sense

Nov 24, 2013 by Kevin Begos
In this Thursday, Nov. 21, 2013 photo, Abhinav Gupta, left, stands with Abhinav Shrivastava as they look over one of the clusters of computers used in their research at one of the computer server areas on campus at Carnegie Mellon University in Pittsburgh. The school is letting hundreds of computers run constantly to scan millions of images off the Internet, and have the computers make connections on their own. The plan is to let the system run forever. (AP Photo/Keith Srakocic)

Researchers are trying to plant a digital seed for artificial intelligence by letting a massive computer system browse millions of pictures and decide for itself what they all mean.

The system at Carnegie Mellon University is called NEIL, short for Never Ending Image Learning. In mid-July, it began searching the Internet for images 24/7 and, in tiny steps, is deciding for itself how those images relate to each other. The goal is to recreate what we call common sense—the ability to learn things without being specifically taught.

It's a new approach in the quest to solve computing's Holy Grail: getting a machine to think on its own using a form of common sense. The project is being funded by Google and the Department of Defense's Office of Naval Research.

"Any intelligent being needs to have common sense to make decisions," said Abhinav Gupta, a professor in the Carnegie Mellon Robotics Institute.

NEIL uses advances in vision to analyze and identify the shapes and colors in pictures, but it is also slowly discovering connections between objects on its own. For example, the computers have figured out that zebras tend to be found in savannahs and that tigers look somewhat like zebras.

In just over four months, the network of 200 processors has identified 1,500 objects and 1,200 scenes and has connected the dots to make 2,500 associations.

Some of NEIL's computer-generated associations are wrong, such as "rhino can be a kind of antelope," while some are odd, such as "actor can be found in jail cell" or "news anchor can look similar to Barack Obama."

In this Thursday, Nov. 21, 2013 photo, Abhinav Gupta stands near one of the computer clusters used in his research at one of the computer server areas on campus at Carnegie Mellon University in Pittsburgh. The school is letting hundreds of computers run constantly to scan millions of images off the Internet, and have the computers make connections on their own. The plan is to let the system run forever. (AP Photo/Keith Srakocic)

But Gupta said having a computer make its own associations is an entirely different type of challenge than programming a supercomputer to do one thing very well, or fast. For example, in 1985, Carnegie Mellon researchers programmed a computer to play chess; 12 years later, a computer beat world chess champion Garry Kasparov in a match.

Catherine Havasi, an artificial intelligence expert at the Massachusetts Institute of Technology, said humans constantly make decisions using "this huge body of unspoken assumptions," while computers don't. She said humans can also quickly respond to some questions that would take a computer longer to figure out.

"Could a giraffe fit in your car?" she asked. "We'd have an answer, even though we haven't thought about it" in the sense of calculating the giraffe's body mass.

Robert Sloan, an expert on and head of the Department of Computer Science at the University of Illinois, Chicago, said the NEIL approach could yield interesting results because just using language to teach a computer "has all sorts of problems unto itself."

"What I would be especially impressed by is if they can consistently say 'zebra, zebra, zebra' if they see the animal in different locations," Sloan said of the computers.

Gupta is pleased with the initial progress. In the future, NEIL will analyze vast numbers of YouTube videos to look for connections between objects.

"When we started the project, we were not sure it would work," he said. "This is just the start."

Neither Mountain View, California-based Google Inc. nor the Office of Naval Research responded to questions about why they're funding NEIL, but there are some hints. The Naval Research website notes that "today's battlespace environment is much more complex than in the past" and that "the rate at which data is arriving into the decision-making system is growing, while the number of humans available to convert the data to actionable intelligence is decreasing."

In other words, computers may make some of the decisions in future wars. The Navy's website notes: "In many operational scenarios, the human presence is not an option."

NEIL's motto is "I Crawl, I See, I Learn," and the researchers hope to keep NEIL running forever. That means the computer might get a lot smarter.

Or it might not.

Explore further: Innovative new supercomputers increase nation's computational capacity and capability

4.6 /5 (14 votes)
add to favorites email to friend print save as pdf

Related Stories

Computer smart as a 4-year-old

Jul 15, 2013

Artificial and natural knowledge researchers at the University of Illinois at Chicago have IQ-tested one of the best available artificial intelligence systems to see how intelligent it really is.

Bringing 'common sense' to text analytics

Sep 26, 2013

Bringing "common sense" to artificial intelligence is one of the biggest challenges in computer science: It entails equipping computers with the shared knowledge that humans use to infer meaning, make connections ...

Recommended for you

Forging a photo is easy, but how do you spot a fake?

Nov 21, 2014

Faking photographs is not a new phenomenon. The Cottingley Fairies seemed convincing to some in 1917, just as the images recently broadcast on Russian television, purporting to be satellite images showin ...

Algorithm, not live committee, performs author ranking

Nov 21, 2014

Thousands of authors' works enter the public domain each year, but only a small number of them end up being widely available. So how to choose the ones taking center-stage? And how well can a machine-learning ...

Professor proposes alternative to 'Turing Test'

Nov 19, 2014

(Phys.org) —A Georgia Tech professor is offering an alternative to the celebrated "Turing Test" to determine whether a machine or computer program exhibits human-level intelligence. The Turing Test - originally ...

Image descriptions from computers show gains

Nov 18, 2014

"Man in black shirt is playing guitar." "Man in blue wetsuit is surfing on wave." "Black and white dog jumps over bar." The picture captions were not written by humans but through software capable of accurately ...

User comments : 3

Adjust slider to filter visible comments by rank

Display comments: newest first

SDrapak
5 / 5 (2) Nov 24, 2013
I would suspect that the first computers with common sense would start by getting rid of the stupid humans who can't figure out how to stop crapping where they live
Sinister1811
not rated yet Nov 24, 2013
Let's hope it doesn't learn common sense from this woman
http://www.dailym...ard.html
antialias_physorg
not rated yet Nov 25, 2013
I would suspect that the first computers with common sense would start by getting rid of the stupid humans who can't figure out how to stop crapping where they live

Little chance of that. Computers aren't born with instincts. And instincts are what would cause a reaction (computers have neither the drive to survive, nor do they know anything about fear or any of the other hormonal based emotions humans experience).
So they lack basic drives that would let them jump to conclusions on which to act.

If we want them to have such drives we have to artificially set them up in the program (which can be done). The fault, if anything goes wrong, will be entirely of our own making.

This fear about computers suddenly getting smart and nasty is unfounded. It's antropomorphisation.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.