=========================================================================
CALL FOR PAPERS
NIPS 2013 Workshop on Output Representation Learning
December 9 or 10, 2013
Lake Tahoe, Nevada, USA
http://sites.google.com/site/outputrepresentlearn2013
=========================================================================
Modern data analysis increasingly faces prediction problems that have
complex and high dimensional output spaces: document tagging problems
now regularly consider large, hierarchical sets of output tags; image
tagging problems regularly consider tens of thousands of possible output
labels; natural language processing tasks normally consider complex
output spaces. In response, there is a growing body of work on learning
output representations, distinct from current work on learning input
representations. For example, in machine learning, work on multi-label
learning, and particularly output dimensionality reduction in high
dimensional label spaces, has begun to address the specialized label
problem, while work on output kernel learning has begun to address the
abstracted label problem. In computer vision, work on image
categorization and tagging has begun to investigate simple forms of
latent output representation learning to cope with abstract semantic
labels and large label sets. In speech recognition, dimensionality
reduction has been used to identify abstracted outputs, while hidden
CRFs have been used to identify specialized latent outputs. In
information retrieval and natural language processing, discovering
latent output specializations in complex domains has been an ongoing
research topic for the past half decade.
The aim of this workshop is to bring these relevant research communities
together to identify fundamental strategies, highlight differences, and
identify the prospects for developing a set of systematic theory and
methods for output representation learning.
Topics:
* Output dimensionality reduction methods
* Output dimensionality expansion methods
* Learning output kernels
* Output structure learning
* Coping with partial output labellings
* Reverse direction pre-training in deep models
(Other relevant topics are also welcome.)
Speakers:
-----------
* Dan Roth (University of Illinois at Urbana-Champaign)
* Li Deng (Microsoft Research)
* Samy Bengio (Google Research)
* Kilian Weinberger (Washington University)
* Yoshua Bengio (University of Montreal)
Submission:
-----------
Authors are encouraged to submit short papers in NIPS 2013 format with a
maximum of 4 pages, excluding references. Anonymity is not required.
Relevant works that have been recently published or presented elsewhere
are allowed, provided that previous publications are explicitly
acknowledged.
Please submit papers in PDF format at
https://www.easychair.org/conferences/?conf=orl2013.
Important Dates:
-----------
Submission Deadline: October 9, 2013
Author Notification: October 23, 2013
Workshop: December 9 or 10, 2013
Organizers:
-----------
Yuhong Guo (Temple University)
Dale Schuurmans (University of Alberta)
Richard Zemel (University of Toronto)
Contact:
The organizers can be contacted at [email protected].
_______________________________________________
uai mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/uai
