Artificial Intelligence
A new artificial intelligence learning program can now recognize and draw handwritten characters after seeing them only a few times. The results when compared with a human—a new variant of the Turing Test—are virtually indistinguishable.
Researchers have created an algorithm that mimics human learning abilities, enabling computers to recognize and draw simple visual characters that are mostly indistinguishable from those created by humans. This represents a significant advance in the field of artificial intelligence, shortening the time it takes computers to 'learn' new concepts and broadens their application to more creative tasks.
"We think we have a machine system that can learn a large class of visual concepts in ways that are hard to distinguish from human learners."
The work has been published in the latest issue of the journal Science, and is available for use in a public Git repository.The system was developed by Brendan Lake, a researcher at New York University, working with Ruslan Salakhutdinov, an assistant professor of computer science at the University of Toronto, and Joshua Tenenbaum, a professor in the Department of Brain and Cognitive Sciences at MIT.
"For the first time we think we have a machine system that can learn a large class of visual concepts in ways that are hard to distinguish from human learners," said Joshua Tenenbaum, the senior author of the new paper and a professor at M.I.T., in a teleconference with reporters.
“You show even a young child a horse or a school bus or a skateboard, and they get it from one example,” Tenenbaum said. “If you forget what it's like to be a child, think about the first time you saw, say, a Segway, one of those personal transportation devices, or a smartphone or a laptop. You just needed to see one example and you could then recognize those things from different angles under different lighting conditions, often barely visible in complex scenes with many other objects.”
The essence of the new system is that it can generalize concepts.
Related articles
Current deep learning approaches have resulted in major advances in technologies like facial and speech recognition, but they often still require hundreds, even thousands of examples before they can recognize the shared qualities that allow for such a generalization."On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches," write the researchers.
In their study, the researchers used a technique they call the Bayesian program learning framework, or BPL. They based their work on the Omniglot data set of handwritten characters.
The software generates a unique program for every character using strokes of an imaginary pen. A probabilistic programming technique is then used to match a program to a particular character, or to generate a new program for an unfamiliar one. The software is not mimicking the way children acquire the ability to read and write but, rather, the way adults, who already know how, learn to recognize and re-create new characters.
“The key thing about probabilistic programming—and rather different from the way most of the deep-learning stuff is working—is that it starts with a program that describes the causal processes in the world,” says Tenenbaum. “What we’re trying to learn is not a signature of features, or a pattern of features. We’re trying to learn a program that generates those characters.”
Geoffrey Hinton, a professor of psychology at the University of Toronto, now also at Google who played a key role in the development of deep learning, says the work is an important step for the field. “It’s a beautiful paper, and a very impressive example of learning from not many examples,” he says.
0 comments:
Post a Comment