[hpc-announce] CFP: Parallel Computing for Neural-based Systems (PaCNeS’15)

Masoud Daneshtalab masdan at utu.fi
Fri Jul 18 11:15:25 CDT 2014


(Please accept our apologies for multiple postings of this announcement)

======================================================================================
Call for Paper:
Special Session on Parallel Computing for Neural-based Systems (PaCNeS’15)
at 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2015)
Turku, Finland, March 4th - 6th, 2015

http://www.pdp2015.org/specialsessions/pacnes/pacnes.html
======================================================================================

Scope:
The goal of the Session is to provide an international forum for reporting progress and recent advances
in parallel computing techniques, hardware and software tools for speeding-up functioning and training
of traditional and bio-inspired neural-based systems on the modern high-performance computing systems.
On top of that we are seeking for new type of neural-based computing devices that significantly improve
the existing computing capabilities. Topics of interest include, but are not limited to:

• Specialized computing hardware, transputers and FPGA-implementations for neural-based systems
• Parallel training algorithms for feed-forward, recurrent, RBF, recirculation and other neural-based systems
• Parallel supervised and unsupervised training and reinforcement learning algorithms
• Parallelization of neural network algorithms on many-core systems, clusters, grids and clouds
• GPU-based implementations of neural networks
• Coarse-grain parallelization of neural-based systems
• Parallel training algorithms for deep-belief networks
• Parallelization of cognitive neural models
• Parallel implementations and training algorithms for spiking neural-based systems
• Grid-based frameworks for neural networks execution and parallelization
• Modeling of large-scale neural models using parallel computing techniques
• Neural simulators in neuroscience using parallel computing
• Computational neuroscience using parallel architectures
• Neural network simulation tools and libraries using parallel computing
• High-performance machine intelligence

Proceeding:
Proceedings will be published by the Conference Publishing Services (CPS) in the same
volume of the main track. Authors of accepted papers are expected to register and present
their papers at the Conference. Conference proceedings will be submitted for inclusion in
IEEE explore and the CSDL, and for indexing, among others, to DBLP, Scopus ScienceDirect, and
ISI Web of Knowledge.

Important dates
Paper submission: 25st August 2014
Acceptance notification: 25th Oct 2014
Camera ready due: 10th Nov 2014
Conference: 4th - 6th Mar 2015

Prospective authors should submit a full paper not exceeding 8 pages in the IEEE Conference
proceedings format (IEEEtran, double-column, 10pt). Double-bind review: the first page of the
paper should contain only the title and abstract; in the reference list, references to the authors’
own work should appear as "omitted for blind review" entries.

Submit a PDF copy of your full manuscript to the EasyChair link at (PaCNeS):
https://www.easychair.org/conferences/?conf=pdp2015


Organizers:
Volodymyr Turchenko, Ternopil National Economic University, Ukraine
Masoud Daneshtalab, University of Turku, Finland
Martin Bogdan, Leipzig University, Germany













More information about the hpc-announce mailing list