Faculty Candidate: Luis von Ahn/Carnegie Mellon University Human Computation in ACES 2.302

Contact Name: 
Jenna Whitney
Date: 
Apr 18, 2006 11:00am - 12:00pm


There is a signup schedule for this eve

nt.

Speaker Name/Affiliation: Luis von Ahn/Computer Science Departm

ent Carnegie Mellon University

Talk Title: Human Computation
Date/Time: April 18 2006 at 11:00 a.m.

Coffee: 10:45 a.m.

Location: ACES 2.302

Host: Peter Stone

Talk Abstract:
T

asks like image recognition are trivial for humans but
continue to cha

llenge even the most sophisticated computer
programs. This talk introdu

ces a paradigm for utilizing
human processing power to solve problems t

hat computers
cannot yet solve. Traditional approaches to solving such

problems focus on improving software. I advocate a novel
approach: c

onstructively channel human brainpower using
computer games. For exampl

e the ESP Game described in
this talk is an enjoyable online game --
many people play
over 40 hours a week -- and when people play they he

lp
label images on the Web with descriptive keywords. These
keyword

s can be used to significantly improve the
accuracy of image search. Peo

ple play the game not because
they want to help but because they enjoy
it. The ESP Game
has been licensed by a major Internet company and wil

l soon
become the basis of their image search engine.

I describe
other examples of games with a purpose: Peekaboom
which helps determi

ne the location of objects in images
and Verbosity which collects co

mmon-sense knowledge. I
also explain a general approach for constructin

g games with
a purpose.

In addition I describe my work on CAPTC

HAs automated tests
that humans can pass but computer programs cannot.
CAPTCHAs
take advantage of human processing power in order to differen

tiate
humans from computers an ability that has important applications

in practice.

The results of this work are currently in use by h

undreds
of Web sites and companies around the world and over 100 000 <

br>people have played some of the games presented here. Practical
appli

cations include improvements in areas such as: computer
vision image s

earch adult-content filtering spam prevention
common-sense reasoning
accessibility and security in general.