Skip to footer

Scientists teach computers to learn simple ideas faster – like humans

Researchers affiliated with New York University and Massachusetts Institute of Technology have developed an algorithm that dramatically cuts back on the time it takes for computers to recognize simple concepts. 

|
Courtesy of Brenden Lake
This screen capture from video shows 20 different people drawing a novel character (left) and the algorithm predicting how those images were drawn (right). This material relates to a paper that appeared in the Dec. 11, 2015 issue of Science, published by AAAS. The paper, by B.M. Lake at New York University in New York, NY, and colleagues was titled, 'Human-level concept learning through probabilistic program induction.'

Researchers at Massachusetts Institute of Technology and New York University have begun to teach computers an algorithm that mirrors the learning techniques practiced by humans – a big step toward reducing the amount of time needed for machines to learn and then practice new concepts.

"It has been very difficult to build machines that require as little data as humans when learning a new concept," Ruslan Salakhutdinov, an assistant professor of computer science at the University of Toronto, said in a news release. "Replicating these abilities is an exciting area of research connecting machine learning, statistics, computer vision, and cognitive science."

The researchers created a probability-based algorithm called a "Bayesian Program Learning" framework. Designed to be self-programming, the algorithm generated new code that produced a new output of the computer program the researchers wanted their software to learn in each successive variation. The results were published online Thursday and in Friday's edition of the journal Science.

This practice mirrors the way humans learn; most human beings require a few brief examples of a new concept before they latch onto it and understand.

Over the course of the self-generating program, the software was able to identify correctly and to draw a handwritten character after seeing just one example. The researchers tested this accuracy by drawing on a database of the world’s written languages, including Sanskrit and Tibetan.

When the researchers showed the results of what their software had drawn to a panel of judges, asking them to compare the computer’s drawings to those made by humans, the judges were unable to distinguish between the humans’ drawings and the computer’s only 25 percent more than chance in each example.

The researchers are excited to explore what the results of this study could portend for other developments in artificial intelligence.

“We are still far from building machines as smart as a human child, but this is the first time we have had a machine able to learn and use a large class of real-world concepts – even simple visual concepts such as handwritten characters – in ways that are hard to tell apart from humans,” Joshua Tenenbaum, a professor at MIT in the Department of Brain and Cognitive Sciences and the Center for Brains, Minds and Machines, said in the release.

You've read  of  free articles. Subscribe to continue.
Real news can be honest, hopeful, credible, constructive.
What is the Monitor difference? Tackling the tough headlines – with humanity. Listening to sources – with respect. Seeing the story that others are missing by reporting what so often gets overlooked: the values that connect us. That’s Monitor reporting – news that changes how you see the world.
editor@csmonitor.com
Subscribe
Mark Sappenfield
Editor

Dear Reader,

About a year ago, I happened upon this statement about the Monitor in the Harvard Business Review – under the charming heading of “do things that don’t interest you”:

“Many things that end up” being meaningful, writes social scientist Joseph Grenny, “have come from conference workshops, articles, or online videos that began as a chore and ended with an insight. My work in Kenya, for example, was heavily influenced by a Christian Science Monitor article I had forced myself to read 10 years earlier. Sometimes, we call things ‘boring’ simply because they lie outside the box we are currently in.”

If you were to come up with a punchline to a joke about the Monitor, that would probably be it. We’re seen as being global, fair, insightful, and perhaps a bit too earnest. We’re the bran muffin of journalism.

But you know what? We change lives. And I’m going to argue that we change lives precisely because we force open that too-small box that most human beings think they live in.

The Monitor is a peculiar little publication that’s hard for the world to figure out. We’re run by a church, but we’re not only for church members and we’re not about converting people. We’re known as being fair even as the world becomes as polarized as at any time since the newspaper’s founding in 1908.

We have a mission beyond circulation, we want to bridge divides. We’re about kicking down the door of thought everywhere and saying, “You are bigger and more capable than you realize. And we can prove it.”

If you’re looking for bran muffin journalism, you can subscribe to the Monitor for $15. You’ll get the Monitor Weekly magazine, the Monitor Daily email, and unlimited access to CSMonitor.com.

Subscribe to insightful journalism

QR Code to Scientists teach computers to learn simple ideas faster – like humans
Read this article in
https://www.csmonitor.com/Technology/2015/1211/Scientists-teach-computers-to-learn-simple-ideas-faster-like-humans
QR Code to Subscription page
Start your subscription today
https://www.csmonitor.com/subscribe