Teaching machine to 'learn' like us

To shorten machine learning, a team of researchers has tried to teach machines to learn like us.

The New York University scientists have developed an algorithm that captures our learning abilities, enabling computers to recognize and draw simple visual concepts that are mostly indistinguishable from those created by humans.

The work marks a significant advance in the field, one that dramatically shortens the time it takes computers to 'learn' new concepts and broadens their application to more creative tasks.

The results show that by reverse engineering how people think about a problem, we can develop better algorithms, explains lead author Brenden Lake. "Moreover, this work points to promising methods to narrow the gap for other machine learning tasks."

When humans are exposed to a new concept, such as new piece of kitchen equipment, a new dance move or a new letter in an unfamiliar alphabet, they often need only a few examples to understand its make-up and recognize new instances. While machines can now replicate some pattern-recognition tasks previously done only by humans, ATMs reading the numbers written on a check, for instance, machines typically need to be given hundreds or thousands of examples to perform with similar accuracy.

Researcher Joshua Tenenbaum noted that they are still far from building machines as smart as a human child, but this is the first time they 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.

The study appears in Science.