<body>
<p>
*** Last reminder ***
</p>
<p>
<h3>Special Session on Learning and Modeling Big Data</h3>
at
<a href="http://www.esann.org">ESANN 2014</a>,
23-25 April 2014, Bruges, Belgium,
</p>
<p>
<b>Organizers:</b> Barbara Hammer (Bielefeld University, DE), Haibo He (Rhode Island, USA), Thomas Martinetz (University of Luebeck, DE)
</p>
<p>
<b>Abstract:</b>
Big data in the sense of large or streaming data sets, very high dimensionality, or complex data formats constitute one of the major challenges faced by machine learning today, caused by powerful sensors and digitalization techniques as well as dramatically increased storage capabilities. In this realm, a couple of typical assumptions of machine learning can no longer be met, causing the need for novel algorithmic developments and paradigm shifts, such as
<ul>
<li> online learning and techniques for streaming data
<li> learning from non i.i.d. data and skewed distributions
<li> life-long adaptation of model complexity and hyper-parameters
<li> linear or sublinear algorithms with limited online memory capacity
<li> parallel implementations
<li> sparse representation of data, efficient information compression
<li> interpretable models
<li> learning from the crowd
<li> good priors in the context of extremely high dimensionality
</ul>
We solicit contributions focussing on novel algorithmic developments, theoretical investigations or applications connected to this non-exhaustive list of topics.
</p>
<p>
<b>Schedule:</b>
<ul>
<li>Paper submission deadline : 29 November 2013
<li>Notification of acceptance : 31 January 2014
<li>Deadline for final papers : 21 February 2014
<li>ESANN 2014 conference : 23-25 April 2014
</ul>
Infos on submissions can be found at
<a href="http://www.elen.ucl.ac.be/esann/index.php?pg=submission">http://www.esann.org</a>
</p>
</body>