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

  • U.S. states uncertain what Trump victory means for wind and solar power

    Tech & Science CBC News
    President Donald Trump has disputed climate change, pledged a revival of coal and disparaged wind power, and his nominee to head the Energy Department was once highly skeptical of the agency's value. What this means for states' efforts to promote renewable energy is an open question. Source
  • N.S. wildlife park fundraising to save 'Little Bear' from euthanasia

    Tech & Science CTV News
    A wildlife park in Cape Breton, N.S., is appealing for donations to build a new cage for an orphaned black bear cub in their care. The nearly one-year-old black bear, dubbed “Little Bear,” was found wandering alone by a pair of men on a highway near Whycocomagh, N.S. Source
  • China's online population reaches 731 million

    Tech & Science CTV News
    The number of internet users in China -- already the world's highest -- reached 731 million in December, authorities said, as e-commerce drives consumer demand across the Asian giant. Total internet users rose 6.2 per cent from the end of December 2015 and equals the entire population of Europe, the government-linked China Internet Network Information Center (CNNIC) said in a statement Sunday on its website. Source
  • Samsung: Batteries only problem with fire-prone Note 7s

    Tech & Science Toronto Sun
    SEOUL, Korea, Republic Of — Samsung Electronics Co. said Monday that problems with the design and manufacturing of batteries in its Galaxy Note 7 smartphones caused them to overheat and burst into fire. The announcement of results from the company’s investigation into one of its worst product fiascos comes three months after the flagship phone was discontinued. Source
  • Ribbon may have finally run out for India's typewriters

    Tech & Science CTV News
    NEW DELHI -- The end is coming, though admittedly it may not look that way at 10 a.m. on a Tuesday morning, when dozens of young Indians have arrived for morning classes at Anand Type, Shorthand and Keypunch College, and every battered Remington is clattering away. Source
  • China cracks down on VPN devices used to access blocked sites

    Tech & Science CTV News
    BEIJING -- A Chinese technology regulator has announced a 14-month campaign to root out services that allow people in the country to circumvent the government's internet censorship. The Ministry of Industry and Information Technology says it forbids the use of virtual private networks (VPNs) or leased lines that allow users and businesses to access blocked overseas websites without permission. Source
  • Researchers say mackerel and a volcano eruption provide clue about climate change

    Tech & Science CTV News
    PORTLAND, Maine - What could an Indonesian volcanic eruption, a 200-year-old climate disaster and a surge in the consumption of mackerel tell us about today's era of global warming? Quite a bit, researchers say. Source
  • Samsung blames Galaxy Note 7 smartphone fires on battery design, manufacturing

    Tech & Science CBC News
    Samsung Electronics Co. says problems with the design and manufacturing of batteries in its Galaxy Note 7 smartphones caused them to overheat and burst into fire. The announcement Sunday of the company's investigation into one of its worst product fiascos comes three months after the flagship phone was discontinued. Source
  • Battery defects led to fires in Note 7 phones: Samsung

    Tech & Science CTV News
    SEOUL, Korea, Republic Of - Samsung Electronics said Monday that after testing more than 200,000 Galaxy Note 7 smartphones, it found defects in two sets of batteries from two different manufacturers made the devices prone to catch fire. Source
  • Samsung: Note 7 battery design, manufacturing caused fires

    Tech & Science Toronto Sun
    SEOUL, Korea, Republic Of — Samsung Electronics Co. said Monday that problems with the design and manufacturing of batteries in its Galaxy Note 7 smartphones caused them to overheat and burst into fire. The announcement of results from the company’s investigation into one of its worst product fiascos comes three months after the flagship phone was discontinued. Source