[Research] Fwd: LTI Colloquium, this Friday (6 Sept), Andrew Moore

[Artur Dubrawski]

FYI



-------- Original Message --------
Subject: 	LTI Colloquium, this Friday (6 Sept), Andrew Moore
Date: 	Sat, 31 Aug 2013 13:44:50 -0400
From: 	bhiksha raj <bhiksha at cs.cmu.edu>
To: 	LTI-students <lti-students at cs.cmu.edu>,
"lti-faculty-all at cs.cmu.edu" <lti-faculty-all at cs.cmu.edu>,
ml-faculty at cs.cmu.edu, ml-students at cs.cmu.edu, ece-faculty at ece.cmu.edu,
ece-students at ece.cmu.edu, Laurie Heller <hellerl at andrew.cmu.edu>



Dear All

We have a colloquium this Friday by our own Andrew Moore.
Details below.

-Bhiksha
-----------------------------------------

LTI Colloquium
Location: 2315 Doherty Hall
Time:  2.30-3.50pm,   Friday, 6th September 2013
Speaker : Andrew Moore  (Google)

Title:   Computational Statistics meets Fashion

Abstract:

I will present some of the computer vision and machine learning
technology behind fashion and shopping results in Google. The aim is to
provide a personalized experience for fashion of the same kind of flavor
that Pandora does in music or Netflix does in movies. There are many
technological challenges in achieving a great user experience. Users
expect close to no errors, especially when it comes to personalized
results. As a result, we developed advanced algorithms for segmentation
and auto-tagging of images. The talk will illustrate first a technical
demo, followed by a dive-in to the algorithmic details of segmentation,
visual search and some components of auto-tagging. Google has recently
started launching these experiences on Google Shopping in order to have
a wider reach to its users.

Speaker Bio:

Andrew Moore, Vice President - Engineering, Google, is responsible for
building products and new technology for Google’s efforts in Ads and
Commerce. Andrew is also site lead for Google's Pittsburgh office, which
develops core machine learning and systems technology behind many of
Google’s advertising quality systems. It is also the home of the
numerical and statistical approaches for Google Shopping, new methods
for managing planet-wide fleets of data centers, and (through the
acquisition of PittPatt) computer vision systems for the Android platform.

Prior to joining Google in January 2006, Andrew was a Professor of
Robotics and Computer Science at the School of Computer Science,
Carnegie Mellon University. Andrew began his career writing video-games
for an obscure British personal computer (). He rapidly became a
thousandaire and retired to academia, where he received a PhD from the
University of Cambridge in 1991. He researched robot learning as a
Post-doc working with Chris Atkeson, and then moved to CMU.

Andrew is a AAAI fellow, and co-author of Handbook of Biosurvellance,
and his machine learning tutorial slides have been viewed over a million
times. From 2002-2005 Andrew was co-director of the University of
Pittsburgh's Biomedical Security Center.

-- 
Bhiksha Raj
Carnegie Mellon University
Pittsburgh, PA, USA
Tel: 412 268 9826