

Wednesday, May 14, 2008 • 7:30 PM • Armory for the Arts, 1050 Old Pecos Trail
Peter Norvig Director of Research, Google Inc.
Practice Makes Perfect: How Billions of Examples Lead to Better Models of Language, Pictures, and Other Things
The Internet gives us access to billions of pages of information, along with billions of pictures and hundreds of millions of videos. Of course, a person could never look at all of them, but computers are faster than humans: what can a computer learn from all this
information? A computer might not learn in the same way that a person does, but it can use massive amounts of data to perform selected tasks very well. It can correct spelling mistakes, translate from Arabic to English, and recognize celebrity faces about as well as an average human—and can do it all by learning from examples rather than by relying on programming.
This lecture is underwritten by RedfishGroup, Santa Fe
