Peter Norvig - The Unreasonable Effectiveness of Data

How Billions of Trivial Data Points can Lead to Understanding

Peter Norvig (Director of Research, Google) presents as part of the UBC Department of Computer Science's Distinguished Lecture Series, September 23, 2010.

In decades past, models of human language were wrought from the sweat and pencils of linguists. In the modern day, it is more common to think of language modeling as an exercise in probabilistic inference from data: we observe how words and combinations of words are used, and from that build computer models of what the phrases mean. This approach is hopeless with a small amount of data, but somewhere in the range of millions or billions of examples, we pass a threshold, and the hopeless suddenly becomes effective, and computer models sometimes meet or exceed human performance. This talk gives examples of the data available in large repositories of text, images, and videos, and shows some tasks that can be accomplished with the resulting models.

• Category

  Education

[thinley108]

part starting 24:50 is very funny

[rangjungyeshe]

Very interesting insights in how comp sci is now using inference from data to solve problems previously tackled by rules. Maybe this is closer to how humans learn languages....it sure isn't by learning all that grammar...

[57v60n85t]

Although it is an enlightening talk, the graph at 52:00 is slightly misleading. If you set the lower limit of y-axis to zero, you will see what I mean.

[kirkbutler12]

Right! Strange feedback for this video once again.

[leighstephens74]

This vid is popular on Kabul