Today's artificial intelligence may not be that clever, but it just got much quicker in understanding. A learning program designed by three researchers can now recognize and draw handwritten characters after seeing them only a few times, just as a human can. And the program can do it so well that people can't tell the difference.
The findings, published in the journal Science, represent a major step forward in developing more powerful computer programs that learn in the ways that humans do.
Although computers are excellent at storing and processing data, they're less-than-stellar students. Your average 3-year-olds could pick up basic concepts faster than the most advanced program.
In short, "You can generalize," said coauthor Joshua Tenenbaum. But there's something else humans can do with just a little exposure—they can break an object down into its key parts and dream up something new. "To scientists like me who study the mind, the gap between machine-learning and human-learning capacities remains vast," Tenenbaum said. "We want to close that gap, and that's our long-term goal."
Now, Tenenbaum and his colleagues have managed to build a different kind of machine learning algorithm (算法)—one that, like humans, can learn a simple concept from very few examples and can even apply it in new ways. The researchers tested the model on human handwriting, which can vary sharply from person to person, even when each produces the exact same character.
The scientists built an algorithm with an approach called Bayesian program learning, or BPL, a probability-based program. This algorithm is actually able to build concepts as it goes.
In a set of experiments, the scientists tested the program using many examples of 1,623 handwritten characters from 50 different writing systems from around the world. In a one-shot classification challenge, people were quite good at it, with an average error rate of 4.5 percent. But BPL, slightly edged them out, with a comparable error rate of 3.3 percent. The scientists also challenged the program and some human participants to draw new versions of various characters they presented. They then had human judges determine which ones were made by man and which were made by machine. As it turned out, the humans were barely as good as chance at figuring out which set of characters was machine-produced and which was created by humans.
The findings could be used to improve a variety of technologies in the near term, including for other symbol-based systems such as gestures, dance moves and spoken and signed language. But the research could also shed fresh light on how learning happens in young humans, the scientists pointed out.
