New algorithm lets machines learn like humans

Scientists have created a new algorithm that captures human-like learning abilities. The algorithm enables computers to recognize and draw simple handwritten characters after exposure to just a few examples.

See Full Article

Their work, summarized in an article published Thursday in the journal Science, represents a major advancement in the field of machine learning.

The new algorithm, called “Bayesian Program Learning,” attempts to mimic the way humans learn new concepts. When humans are exposed to a new concept – say a new symbol or object– they can often recognize and understand the new concept after being exposed to it just a few times.

During a teleconference, U of T assistant computer science professor and article co-author Ruslan Salakhutdinov, gave the example of thumbs-up or high-five gestures that humans can recognize and perform as needed, after limited exposure to them.

While there are now machines and programs that can also learn to recognize symbols and patterns, for example object or speech recognition, these machines often depend on tens or hundreds of examples in order to function accurately.

But the new algorithm can recognize and learn a new concept after a limited number of examples, the authors of the study say. As well, the algorithm can perform more creative tasks beyond simple recognition. These tasks include generating new concepts, breaking down concepts into their respective parts, and understanding the relationship between those respective parts.

Salakhutdinov said the algorithm is a significant advancement in the field of artificial intelligence.

"It has been very difficult to build machines that require as little data as humans when learning a new concept," he said in a statement. "Replicating these abilities is an exciting area of research connecting machine learning, statistics, computer vision, and cognitive science."

Recognizing and reproducing handwritten characters

Using the algorithm, a computer was able to create a copy of handwritten characters, after being shown an example. In this case, the new characters were letters from different alphabets from around the world.

The computer was also able to mimic the way humans draw characters, by using similar pen strokes, stroke order and direction, the researchers said.

Finally, the computer was able to generate a totally new character when shown a set and asked to produce another one to be included in the set.

When the researchers compared the computer-generated results with characters produced by humans, they found them to be "mostly indistinguishable."

Machine learning

Can you tell the difference between humans and machines? Humans and machines were given an image of a novel character (top) and asked to produce new exemplars. The nine-character grids in each pair that were generated by a machine are (by row) B, A; A, B; A, B. (Photo courtesy Brenden Lake)

Machine learning

Can you tell the difference between humans and machines? Humans and machines were given an image of a novel character (top) and asked to produce new exemplars. The nine character grids in each pair that were generated by a machine are (by row) 1, 2; 2, 1; 1, 1. (Photo courtesy Brenden Lake)

Brenden Lake, the study's lead author and a Moore-Sloan Data Science Fellow at New York University, said the algorithm can lead to the development of better learning machines.

"Our results show that by reverse engineering how people think about a problem, we can develop better algorithms," he said in a statement. "Moreover, this work points to promising methods to narrow the gap for other machine learning tasks."

Joshua Tenenbaum, a professor at MIT in the Department of Brain and Cognitive Sciences and the Center for Brains, Minds and Machines and a co-author of the article, echoed the sentiment.

"I've wanted to build models of these remarkable abilities since my own doctoral work in the late nineties," he said in a statement. "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."

'Bayesian Program Learning'

The algorithm works by representing concepts as simple computer programs.

For example, the letter "A" is represented by computer code, which will generate examples of that letter when the code is run, NYU said in a statement released Thursday.

However, no human programmer is required during the learning process, rather, the algorithm programs itself by building code to produce the letter it sees. And, unlike standard computer programs that produce the same output every time, these special programs produce different outputs every time they’re run, the statement said.

This captures the variation that exists among concepts, such as the natural differences between how two people might draw the letter "A," the statement added.

In a video explaining his work, Lake said that while the algorithm only currently works for handwritten characters, it could eventually be used in other domains.

"The key point is that we need to learn the right form of representation, not just learning from bigger data sets, in order to build more powerful and more human-like learning patterns," he said.



Advertisements

Latest Tech & Science News

  • Walmart diving into voice-activated shopping with Google

    Tech & Science CTV News
    NEW YORK - Walmart is diving into voice-activated shopping. But unlike online leader Amazon, it's not doing it alone. The world's largest retailer said Wednesday it's working with Google to offer hundreds of thousands of items from laundry detergent to Legos for voice shopping through Google Assistant. Source
  • U.S. government backs down on request for visitor logs of Trump protest website

    Tech & Science CBC News
    The U.S. government is revising its request for data from an anti-Trump protest site to exclude a log of its visitors, according to a brief filed in Superior Court today, saying it has "no interest" in the records. Source
  • Researchers harness human waste to make products in space

    Tech & Science CBC News
    Deep space missions come with challenges, not the least of which is limited storage space. But scientists are finding ways to reduce the amount of supplies and costly shipments astronauts need on missions, partly by making use of what's already on hand — including human waste. Source
  • Researchers harness human urine to make products in space

    Tech & Science CBC News
    Deep space missions come with challenges, not the least of which is limited storage space. But scientists are finding ways to reduce the amount of supplies and costly shipments astronauts need on missions, partly by making use of what's already on hand — including human waste. Source
  • Two newest astronauts moonstruck as Canada looks beyond space station

    Tech & Science CTV News
    MONTREAL -- Canada's two newest astronauts are already looking beyond the International Space Station as they begin two years of intense basic training. Joshua Kutryk points out that Canada is committed to the space station until 2024 along with its international partners. Source
  • Farming has changed climate almost as much as deforestation

    Tech & Science CBC News
    Agriculture has contributed nearly as much to climate change as deforestation by intensifying global warming, according to U.S. research that has quantified the amount of carbon taken from the soil by farming. Some 121 billion tonnes (133 billion tons) of carbon have been removed from the top two metres of the earth's soil over the last two centuries by agriculture at a rate that is increasing, said the study in PNAS, a journal published by the National Academy of Sciences. Source
  • Water down your whisky for better flavour: scientists

    Tech & Science CBC News
    On the rocks, neat, or with water? Ask whisky fans and you'll find it's a contentious topic. However, researchers in Sweden say mixing your scotch with water is the best way to maximize the flavours. Source
  • Parents warned to monitor teen use of app Sarahah

    Tech & Science CTV News
    WINNIPEG - The Canadian Centre for Child Protection is warning parents of the dangers of an app popular with teens called Sarahah. The app allows users to send anonymous "constructive criticism" to friends and co-workers, but critics say it has turned into a platform for cyberbullying and harassment. Source
  • Canada's new astronauts take tips from veterans in space

    Tech & Science CBC News
    Canada's two new astronaut recruits will get a chance to pick the brains of the experienced astronauts currently working aboard the space station today. They'll also speak publicly for the last time before heading for two years of intensive basic training at Johnson Space Center in Houston, Texas. Source
  • Google's next version of Android will be called 'Oreo'

    Tech & Science CBC News
    An upcoming update to Google's Android software finally has a delectable name. The next version will be known as Oreo, extending Google's tradition of naming each version after a sweet treat. L’ready or not, you’ve made it to the sweet treat hall of fame. Source