ISCA - International Speech
Communication Association


ISCApad Archive  »  2015  »  ISCApad #209  »  Events  »  Other Events  »  (2016-05-02) 4th International Conference on Learning Representations (ICLR 2016), San Juan, Puerto Rico,

ISCApad #209

Wednesday, November 11, 2015 by Chris Wellekens

3-3-12 (2016-05-02) 4th International Conference on Learning Representations (ICLR 2016), San Juan, Puerto Rico,
  

4th International Conference on Learning Representations (ICLR 2016)
====================================================================

Website: http://www.iclr.cc/
Submission deadline for title and abstract: 5:00 pm EST, November 12th, 2015
Submission deadline for arXiv paper ID: 5:00 pm EST, November 19th, 2015
Location: Caribe Hilton, San Juan, Puerto Rico, May 2-4, 2016

Overview
--------
It is well understood that the performance of machine learning methods
is heavily dependent on the choice of data representation (or
features) on which they are applied. The rapidly developing field of
representation learning is concerned with questions surrounding how we
can best learn meaningful and useful representations of data. We take
a broad view of the field, and include in it topics such as deep
learning and feature learning, metric learning, kernel learning,
compositional models, non-linear structured prediction, and issues
regarding non-convex optimization.

Despite the importance of representation learning to machine learning
and to application areas such as vision, speech, audio and NLP, there
was no venue for researchers who share a common interest in this
topic. The goal of ICLR has been to help fill this void.

A non-exhaustive list of relevant topics:
 - unsupervised, semisupervised, and supervised representation
   learning
 - metric learning and kernel learning
 - dimensionality expansion
 - sparse modeling
 - hierarchical models
 - optimization for representation learning
 - learning representations of outputs or states
 - implementation issues, parallelization, software platforms,
   hardware
 - applications in vision, audio, speech, natural language processing,
   robotics, neuroscience, or any other field

The program will include keynote presentations from invited speakers,
oral presentations, and posters.

ICLR's Two Tracks
-----------------
As usual, ICLR will feature two tracks: a Conference Track and a
Workshop Track. However, this year, conference and workshop
submissions will be reviewed separately, in two different
periods. This call for paper is thus only for conference
contributions. Workshop submissions will be received a few months
before the conference and be subject to a lighter review. A future
call for papers will be sent with more details on the Workshop Track.

Also, the reviewing period for conference submissions will be
separated into two short rounds (normally 2 reviews in the first
round, 1 review in the second round). The first round will run as
usual. The second round reviews, however, in addition to evaluating
the submissions, will be required to include comments on the content
of the first round reviews. By asking for such comments, we hope to
ensure a minimum of discussion for every paper, and favour
interactions that might either identify factual errors early or reveal
a clearer consensus. Note that some of the submitted conference track
papers that are not accepted to the conference proceedings will be
invited to be presented under the Workshop Track.

ICLR Submission Instructions
----------------------------
By November 12th, authors are asked to enter in openreview.net the
title, abstract and author list for their paper, along with
conflict information.  Then, as soon as possible, authors must
post on arXiv their submission: http://arxiv.org.  Finally, by
November 19th, authors must update their submission in
openreview.net with the arXiv ID of their paper.

Note that there can be up to 3 days of delay between sending a
manuscript on arXiv and receiving your arXiv ID. It is thus important
to post your submission on arXiv early. Note also that you can always
update your submission on arXiv later on, anytime during the review
process. Submissions without an arXiv ID after November 19th will be
automatically removed from openreview.net.

Remember to download the style files and paper template and use within
LaTeX to format your paper. Use of the ICLR 2016 style is mandatory.

When you make your arXiv submission, please be sure to correctly
classify your submission into CoRR categories. Typically, you should
consider the following categories:

  CS.LG: machine learning
  CS.NE: neural networks
  CS.CV: computer vision
  CS.CL: computational linguistics

Virtually all of the ICLR papers should have both CS.LG and CS.NE as
categories and then additional categories depending on the nature of
the problem.

Submission deadline: 11:59 pm PST, November 12th for title and
abstract, 11:59 pm PST, November 19th for arXiv ID.

Notes
-----
Regarding the conference submission's 6-9 page limits, these are
really meant as guidelines and will not be strictly enforced. For
example, figures should not be shrunk to illegible size to fit
within the page limit. However, in order to ensure a reasonable
workload for our reviewers, papers that go beyond the 9 pages
should be formatted to include a 9 page submission, with
supplementary material appended at the end of the manuscript and
clearly marked as an appendix, which will be optionally reviewed.

Paper revisions will be permitted, and in fact are encouraged, in
response to comments from and discussions with the reviewers (see
An Open Reviewing Paradigm below).

An Open Reviewing Paradigm
--------------------------
1.  Submissions to ICLR are posted on arXiv prior to being submitted
    to the conference.
2.  Authors submit their paper to either the ICLR conference track or
    workshop track via the openreview.net ICLR 2016 website.
3.  After the authors have submitted their papers via openreview.net,
    the ICLR program committee designates anonymous reviewers as
    usual.
4.  The submitted reviews are published without the name of the
    reviewer, but with an indication that they are the designated
    reviews.
5.  Anyone can openly (non-anonymously) write and publish comments on
    the paper. Anyone can ask the program chairs for permission to
    become an anonymous designated reviewer (open bidding). The
    program chairs have ultimate control over the publication of each
    anonymous review. Open commenters will have to use their real
    names, linked with their Google Scholar profiles.
6.  Authors can post comments in response to reviews and
    comments. They can revise the paper as many times as they want,
    possibly citing some of the reviews. Reviewers are expected to
    revise their reviews in light of paper revisions.
7.  The review calendar includes a generous amount of time for
    discussion between the authors, anonymous reviewers, and open
    commentators. The goal is to improve the quality of the final
    submissions.
8.  The ICLR program and area chairs will consider all submitted
    papers, comments, and reviews and will decide which papers are to
    be presented in the conference track, which will be invited to be
    presented in the workshop track, and which will not appear at
    ICLR.
9.  Papers that are presented in the workshop track or are not
    accepted will be considered non-archival, and may be submitted
    elsewhere (modified or not), although the ICLR site will maintain
    the reviews, the comments, and the links to the arXiv versions.

General Chairs
--------------
Yoshua Bengio, Université de Montreal
Yann LeCun, New York University and Facebook

Senior Program Chair
--------------------
Hugo Larochelle, Twitter and Université de Sherbrooke

Program Chairs
--------------
Brian Kingsbury, IBM
Samy Bengio, Google

Contact
-------
The organizers can be contacted at iclr2016.programchairs@gmail.com


Back  Top


 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA