Lalish-Menagh, Trevor on 23 Feb 2013 17:12:20 -0800

[Date Prev] [Date Next] [Thread Prev] [Thread Next] [Date Index] [Thread Index]

Fifth A.I. Winter Event: "Learning in the Presence of Malicious Errors" (03/07/2013 6:30PM)

Hi all,

The fifth A.I. Winter event will be held at 03/07/2013 at 6:30pm at the Comcast Center in Center City Philly. Things are really heating up. It is not too late to join in on the fun!

We will be studying the paper "Learning in the Presence of Malicious Errors" by Michael Kearns and Ming Li.
This should be an interesting one. Last time we learned how a machine could learn "on-line," that is without a separate training period. This time we will learn how a machine can learn, even if there is an adversary trying to trick the machine along the way.
Please read the paper beforehand, and come with questions. Remember, you don't have to understand the entire paper to participate. This event is all about communal learning.

Our event will be on the 45th floor of the the Comcast Center. Comcast Interactive Media will be covering pizza and soda for the event.

We'll have beer afterwards at Nodding Head. See you there!

Please RSVP at Doodle.

Notes from the last session on Learning Quickly When Irrelevant Attributes Abound: A New Linear-threshhold Algorithm will be up soon at Thanks to Kinan Faham for taking them!
Don't forget to check in at the event with!

Trevor Lalish-Menagh
@trevmex on twitter

You received this message because you are subscribed to the Google Groups "Philly Lambda" group.
To unsubscribe from this group and stop receiving emails from it, send an email to
For more options, visit