Experts find quicker way to teach a computer

Image: Human vs. machine
This illustration gives a sense of how characters from alphabets around the world were replicated through human vs. machine learning. (Credit: Danqing Wang)

Researchers say they’ve developed an algorithm that can teach a new concept to a computer using just one example, rather than the thousands of examples that are traditionally required for machine learning.

The algorithm takes advantage of a probabilistic approach the researchers call “Bayesian Program Learning,” or BPL. Essentially, the computer generates its own additional examples, and then determines which ones fit the pattern best.

The researchers behind BPL say they’re trying to reproduce the way humans catch on to a new task after seeing it done once – whether it’s a child recognizing a horse, or a mechanic replacing a head gasket.

“The gap between machine learning and human learning capacities remains vast,” said MIT’s Joshua Tenenbaum, one of the authors of a research paper published today in the journal Science. “We want to close that gap, and that’s the long-term goal.”

Get the full story on GeekWire.

By Alan Boyle

Mastermind of Cosmic Log, contributing editor at GeekWire, author of "The Case for Pluto: How a Little Planet Made a Big Difference," president of the Council for the Advancement of Science Writing. Check out "About Alan Boyle" for more fun facts.

Leave a Reply

%d bloggers like this: