[Ml-stat-talks] Fwd: Daphne Koller: October 6, 4:30PM, CS Room 105

David Blei blei at CS.Princeton.EDU
Wed Oct 6 14:43:16 EDT 2010


hi ml-stat-talks

usually we don't post twice, but this one is worth a reminder.

best
dave



---------- Forwarded message ----------
From: David Blei <blei at cs.princeton.edu>
Date: Sun, Oct 3, 2010 at 12:46 PM
Subject: Daphne Koller: October 6, 4:30PM, CS Room 105
To: ml-stat-talks <ml-stat-talks at lists.cs.princeton.edu>


hi ml-stat-talks---

daphne koller (stanford) is speaking at the CS distinguished speakers
series this wednesday 10/6 at 4:30PM.  refreshments are served in the
tea room at 4PM.  (the tea room is on the 2nd floor.)

daphne is among the best and most influential machine learning and
artificial intelligence faculty.  i highly recommend this talk.
details are below.

best
dave


--------------------------------------------------------------------------------
Probabilistic Models for Holistic Scene Understanding

Daphne Koller
Stanford University

Wednesday, October 6, 4:30PM
Computer Science Room 105
--------------------------------------------------------------------------------

ABSTRACT

Over recent years, computer vision has made great strides towards
annotating parts of an image with symbolic labels, such as object
categories or segment types.  However, we are still far from the
ultimate goal of providing a semantic description of an image, such as
"a man, walking a dog on a sidewalk, carrying a backpack".  In this
talk, I will describe our work in this direction, which uses machine
learning to construct richly structured, probabilistic models of
multiple scene components.  We demonstrate the value of such modeling
for improvements in basic tasks such as image segmentation and object
detection, as well as for making more semantic distinctions regarding
shape and activity.  The learning of such expressive models poses new
challenges, especially when available training data is limited or only
weakly labeled.  I will describe novel machine learning methods that
can train models using distantly or weakly labeled data, thereby
making use of much larger amounts of available data.

BIO: Daphne Koller received her BSc and MSc degrees from the Hebrew
University of Jerusalem, Israel, and her PhD from Stanford University
in 1993.  After a two-year postdoc at Berkeley, she returned to
Stanford, where she is now a Professor in the Computer Science
Department.  Her main research interest is in developing and using
machine learning and probabilistic methods to model and analyze
complex domains.  Her current research projects include models in
computational biology and in extracting semantic meaning from sensor
data of the physical world.  Daphne Koller is the author of over 150
refereed publications, which have appeared in venues spanning Science,
Nature Genetics, the Journal of Games and Economic Behavior, and a
variety of conferences and journals in AI and Computer Science.  She
has received 9 best paper or best student paper awards, in conferences
whose areas span computer vision (ECCV), artificial intelligence
(IJCAI), natural language (EMNLP), machine learning (NIPS and UAI),
and computational biology (ISMB).  She has given keynote talks at over
10 different major conferences, also spanning a variety of areas.  She
was the program co-chair of the NIPS 2007 and UAI 2001 conferences,
and has served on numerous program committees and as associate editor
of the Journal of Artificial Intelligence Research and of the Machine
Learning Journal.  She was awarded the Arthur Samuel Thesis Award in
1994, the Sloan Foundation Faculty Fellowship in 1996, the ONR Young
Investigator Award in 1998, the Presidential Early Career Award for
Scientists and Engineers (PECASE) in 1999, the IJCAI Computers and
Thought Award in 2001, the Cox Medal for excellence in fostering
undergraduate research at Stanford in 2003, the MacArthur Foundation
Fellowship in 2004, the ACM/Infosys award in 2008, and the Rajeev
Motwani Endowed Chair in 2010.


More information about the Ml-stat-talks mailing list