Print

Print


Michael,
Can you forward to the CSSA mailing list?

Thanks!

-mp

---------- Forwarded message ----------
From: Michael Pellon <[log in to unmask]>
Date: Tue, Apr 28, 2009 at 2:44 PM
Subject: TALK: "Leveraging the Cloud for Research", Monday, May 4th 1PM
To: Maggie Eppstein <[log in to unmask]>, Peter Sheridan Dodds <
[log in to unmask]>, [log in to unmask], [log in to unmask], [log in to unmask],
[log in to unmask], [log in to unmask], [log in to unmask],
[log in to unmask], [log in to unmask], [log in to unmask],
[log in to unmask], [log in to unmask]


All,

Due to popular request from a couple of you I will be giving a little
informal talk this coming Monday (May 4) in the Farrell Hall Decision
theater (Trinity campus) at 1 PM.

The goal will be to share my experience as a beta tester of Amazon's new
suite of cloud computing resources for both research purposes (analyzing
massive sets of textual data) and as a technical advisor for a small
for-profit company (http://www.fictionaut.com) with hundreds of thousands of
daily visitors that relies on Amazon's "cloud" entirely for its technical
infrastructure.

These cloud computing resources are massive systems (in the order of
millions) of interlinked commodity servers scattered around the globe that
exhibit immense flexibility in their ability to move computation and data
across computers within a cluster, across clusters of computers and—of
course—between clusters and end user devices. The result is the efficient,
even awesome, capability to provide communication, computation and data to a
vast collection of people and applications.

Formally titled "Leveraging the Cloud for Research : Ideal Distributed
Computing" the content will be highly technical in nature with a focus not
only on how these technologies work in general but  how you can utilize them
today for your research through a number of common, robust interfaces.

Time will also be spent on how to obtain FREE sources for data online,
including scrapping/processing raw HTML, Amazon's public data sets and a
number of APIs that allow access to raw data such as the New York Times,
Kiva, GOP.org, Zillow Real Estate, etc.

The presentation will be short (~ 18 minutes, TED style) with the remainder
of the time geared towards an informal discussion within our
computing/research community about the relative advantages/disadvantages of
these emerging cloud computing resources (Amazon Web Services, Google App
Engine, etc.) and their potential role in future research projects here at
UVM that involve massive data sets or intensive computation tasks.

Hope to see you there and Feel free to pass along!

--

Michael Pellon

Graduate Student, UVM Computer Science
Technical Advisor, Teko Labs and Fictionaut.com

Farrell Rm. 204
mpellon [at] trinity [dot] edu


***Disclaimer: The use of trade, firm, or corporation names in this
publication (or page) is for the information and convenience of the reader.
Such use does not constitute an official endorsement or approval by
Amazon.com, Inc. or Google, Inc. of any product or service to the exclusion
of others that may be suitable.



-- 
~mp