[info] Connectionists: Call for Papers: IJCNN07 workshop on "Applications of Neural Networks in High Assurance Systems"

[Eugen Leitl]

----- Forwarded message from Johann Schumann <schumann at email.arc.nasa.gov> -----

From: Johann Schumann <schumann at email.arc.nasa.gov>
Date: Fri, 11 May 2007 22:00:35 -0700
To: connectionists at cs.cmu.edu
Subject: Connectionists: Call for Papers: IJCNN07 workshop on "Applications
 of Neural Networks in High Assurance Systems"
User-Agent: Thunderbird 1.5.0.7 (Macintosh/20060909)

 
             CALL FOR ABSTRACTS / PARTICIPATION
             [Our apologies for multiple copies]


      Applications of Neural Networks in High Assurance Systems


                 IJCNN 2007 Postconference Workshop
                 Orlando, Florida, August 17, 2007
   
                 http://ti.arc.nasa.gov/ijcnn07


                * Abstract Submission: May 25, 2007
                * Decision Notification: June 06, 2007


Since the early days of neural network research, the large potential for
applications in many areas has been recognized and exploited. Today
applications include intelligent-adaptive aircraft control, control of
chemical and power plants, steel manufacturing, and financial forecasting.
Nevertheless, the number of successful neural network applications in high
assurance systems is still comparatively limited. Certification and safety
boards have long voiced concerns about safety, correctness, and reliability
of neural networks employed in high assurance and safety-critical systems.
For such systems guarantees a safe and reliable operation under unknown or
changing conditions must be provided. The general uneasiness about neural
networks as being "non-deterministic", "self-modifying", belonging to
"soft-computing" and "artificial intelligence" poses major obstacles in the
successful deployment of such systems in high-risk and complex industrial
applications. The main aim of this workshop is to address three topics:

   * identify main obstacles for successful high assurance applications,
   * discuss possible ways to overcome those, and
   * identify possible techniques/method to enable and simplify 
certification

The purpose of the workshop is to bring together researchers and users of
neural network based systems and to create a forum for discussing recent
advances in industrial application and certification of learning 
systems, to
better understand the practical requirements for developing and 
deploying such
systems, and to inspire research on new methods and techniques for testing,
certification, and standardization.


                             Topics

* Applications of neural network based methods and systems in high
 assurance systems and experience/lessons learned.
* Techniques, tools, and methods to assess and guarantee the performance of
 a neural network, e.g., statistical (Bayesian) methods, rule extraction
 with subsequent V&V, methods for convergence/stability analysis, dynamic
 monitoring, etc.
* Certification techniques that are specifically suitable for learning and
 adaptive systems, and
* Software development, V&V, and certification processes for neural network
 applications.


                           Submission

Please send an abstract (up to 4 pages) or a short technical paper, 
preferably
in PDF format to "schumann at email.arc.nasa.gov" before May 25, 2007.


                       Workshop Organizers

Dr. Johann Schumann, Robust Software Engineering, RIACS/NASA Ames
E-mail: schumann at email.arc.nasa.gov
Phone: 650-604-0941

Yan Liu, PhD,  Motorola Labs, Schaumburg, IL 60193
E-mail: yanliu at motorola.com
Phone: 847-576-4680

                        Program Committee

   * Dejan Desovski, Google Inc.
   * Pramod Gupta, Nemerix Inc.
   * Stephen Jacklin, NASA Ames
   * Yan Liu, Motorola Labs
   * Johann Schumann, RIACS

----- End forwarded message -----
-- 
Eugen* Leitl <a href="http://leitl.org">leitl</a> http://leitl.org
______________________________________________________________
ICBM: 48.07100, 11.36820 http://www.ativel.com http://postbiota.org
8B29F6BE: 099D 78BA 2FD3 B014 B08A  7779 75B0 2443 8B29 F6BE