Saturday, November 24, 2012

I haz a vision

Some recent advances in really hard computer problems:

Deep-learning systems have recently outperformed humans in certain limited recognition tests.

Last year, for example, a program created by scientists at the Swiss A. I. Lab at the University of Lugano won a pattern recognition contest by outperforming both competing software systems and a human expert in identifying images in a database of German traffic signs.

The winning program accurately identified 99.46 percent of the images in a set of 50,000; the top score in a group of 32 human participants was 99.22 percent, and the average for the humans was 98.84 percent.

Getting better at listening, too:

Deep learning was given a particularly audacious display at a conference last month in Tianjin, China, when Richard F. Rashid, Microsoft’s top scientist, gave a lecture in a cavernous auditorium while a computer program recognized his words and simultaneously displayed them in English on a large screen above his head.

Then, in a demonstration that led to stunned applause, he paused after each sentence and the words were translated into Mandarin Chinese characters, accompanied by a simulation of his own voice in that language, which Dr. Rashid has never spoken.

The feat was made possible, in part, by deep-learning techniques that have spurred improvements in the accuracy of speech recognition.


TC said...

I don't know whether to applaud or boo.

Brendan Keefe said...

Oh, sure. No doubt there will be many unsettling and even unsavory applications of these advances. But as a purely scientific matter, it's mighty impressive.

Substance McGravitas said...

Yay! New friends!