[agents] Verification of Systems that Learn (extended deadline)

[Louise Dennis]

Please Note Extended Deadline!!!

****************************************************

                   CALL FOR PAPERS

Symposium on the Verification of Systems that Learn

                     VLEARN 2018

             Liverpool, United Kingdom,

As part of the AISB Convention, 4th-6th April 2018

http://cgi.csc.liv.ac.uk/~lad/vlearning/

****************************************************

-- ABOUT VLEARN --

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 
common perception is that 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.

The Symposium is being sponsored by the UK Network on the Verification 
and Validation of Autonomous Systems (vavas.org).

--INVITED SPEAKERS--

Dr Yair Zick, University of Singapore

Professor Sandor Veres, University of Sheffield

--IMPORTANT DATES --

   * Full papers and abstracts due: 9th February 2018 (extended deadline)

   * Notification: 16th February 2018

   * Camera-ready versions due: 2nd March 2018

-- SUBMISSION INSTRUCTIONS --

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:

    * Verification of learning algorithms.

    * Verification of objective functions.

    * Specification of learned behaviour.

    * Ensuring the learning process is safe (safe learning).

    * Verification and explainability of neural networks.

Full papers and abstracts may present finished work, work in progress or 
be position papers.

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 
(http://aisb2018.csc.liv.ac.uk/AISB2018.tar.gz) and submitted via 
EasyChair (https://easychair.org/conferences/?conf=vlearn18).  
Proceedings of the workshop will be made available on the workshop 
website and published by the AISB.  Depending upon the success of the 
workshop a journal special issue may be organised after the event.

-- PROGRAM COMMITTEE --

Workshop Chairs:

Louise Dennis (University of Liverpool)

Alice Miller (University of Glasgow)

Committee:

Stefano Albrecht (University of Edinburgh)

Luca Bortolussi (University of Trieste)

Michael Fisher (University of Liverpool)

Xiaowei Huang (University of Liverpool)

Alessio Lomuscio (Imperial College, London)

Sandor Veres (University of Sheffield)

-- 
Dr. Louise Dennis,
Department of Computer Science, Room 117, Ashton Building,
University of  Liverpool, Liverpool, L69 3BX,  UK.
http://www.csc.liv.ac.uk/~lad/  phone: +44 151 795 4237