[auton-users] Beat an algorithm, win a prize

[Ajit Singh]

Geoff and I are writing a paper on relational learning, and we would 
like to pit clever humans, with lots of background knowledge, against 
machines that have lots of data. We're using a small movie ratings 
prediction task, where you guess how many stars a user will assign to a 
movie.

We would appreciate it if you could fill out the attached survey. It 
should take about 15 minutes. As a sweetener, the person who predicts 
ratings the best (under squared loss) gets bragging rights and a gift
certificate from Amazon.com.

Thanks
Ajit
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: rating_task.txt
URL: <https://mailman.srv.cs.cmu.edu/mailman/private/autonlab-users/attachments/20070224/33713797/attachment.txt>
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: Instructions.txt
URL: <https://mailman.srv.cs.cmu.edu/mailman/private/autonlab-users/attachments/20070224/33713797/attachment-0001.txt>