We will be studying the paper
"Learning Quickly When Irrelevant Attributes Abound: A New Linear-threshold Algorithm" by Nick Littlestone (http://www.aiwinter.org/papers/6).
This is one of the papers that started the field of on-line learning.
In this learning setting, a learner receives a sequence of examples,
making predictions after each one, and receiving feedback after each
prediction. Research in this area is remarkable because (1) the
algorithms and proofs tend to be very simple and beautiful, and (2) the
model makes no statistical assumptions about the data. In other words,
the data need not be random (as in nearly all other learning models),
but can be chosen arbitrarily by "nature" or even an adversary.
Specifically, this paper introduced the winnow algorithm.
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 (
http://www.doodle.com/m43kuiwyfeetds4h)
Notes from the last session on An Inductive Inference Machine will be up soon at
. Thanks to Kinan Faham for taking them!