<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p>***************************************************
<br>
CALL FOR PAPERS
<br>
Symposium on the Verification of Systems that Learn
<br>
VLEARN 2018
<br>
<br>
Liverpool, United Kingdom,
<br>
As part of the AISB Convention, 4th-6th April 2018
<br>
<br>
<a class="moz-txt-link-freetext"
href="http://cgi.csc.liv.ac.uk/%7Elad/vlearning/">http://cgi.csc.liv.ac.uk/~lad/vlearning/</a>
<br>
****************************************************
<br>
<br>
-- ABOUT VLEARN --
<br>
<br>
Machine learning is of particular value in areas where developing
a precise specification of desired behaviour is outside the scope
of our current understanding of the world. For instance machine
learning is widely deployed for image classification tasks. In
these cases the specification is that the classifier should match
the perception ability of a human. This is a difficult property to
formally specify. Even when properties can be formally specified,
the results of many machine learning systems (e.g. a set of
weights in a neural network) are difficult to map onto these or to
reason about in appropriate terms. The aim of this symposium is
to bring together researchers interested in the question of how
systems that learn may be verified. It will take the form of a
number of scientific presentations and posters.
<br>
</p>
<p>The Symposium is being sponsored by the UK Network on the
Verification and Validation of Autonomous Systems (vavas.org).
<br>
<br>
--INVITED SPEAKER--
<br>
<br>
Professor Sandor Veres, University of Sheffield
<br>
<br>
--IMPORTANT DATES --
<br>
<br>
* Full papers and abstracts due: 26th January 2018
<br>
* Notification: 16th February 2018
<br>
* Camera-ready versions due: 2nd March 2018
<br>
<br>
-- SUBMISSION INSTRUCTIONS --
<br>
<br>
We invite the submission of both full papers (8 pages max) and
extended abstracts (2 pages max) related to the Verification of
Systems that Learn. Relevant topics include, but are not limited
to:
<br>
* Verification of learning algorithms.
<br>
* Verification of objective functions.
<br>
* Specification of learned behaviour.
<br>
* Ensuring the learning process is safe (safe learning).
<br>
* Verification and explainability of neural networks.
<br>
<br>
Full papers and abstracts may present finished work, work in
progress or be position papers.
<br>
<br>
The authors of accepted full papers will be invited to present a
talk at the workshop, while extended abstracts will be invited to
present a poster. Papers should be formatted using the AISB 2018
style (<a class="moz-txt-link-freetext"
href="http://aisb2018.csc.liv.ac.uk/AISB2018.tar.gz">http://aisb2018.csc.liv.ac.uk/AISB2018.tar.gz</a>)
and submitted via EasyChair (<a class="moz-txt-link-freetext"
href="https://easychair.org/conferences/?conf=vlearn18">https://easychair.org/conferences/?conf=vlearn18</a>).
<br>
</p>
<pre class="moz-signature" cols="72">--
Dr. Louise Dennis,
Department of Computer Science, Room 117, Ashton Building, University of Liverpool, Liverpool, L69 3BX, UK.
<a class="moz-txt-link-freetext" href="http://www.csc.liv.ac.uk/~lad/">http://www.csc.liv.ac.uk/~lad/</a> phone: +44 151 795 4237
</pre>
</body>
</html>