IEEE Transactions on
Neural Networks and Learning Systems
Special Issue on Complex- and
Hypercomplex-Valued Neural Networks
Complex-valued neural networks
(CVNNs) exhibit very desirable characteristics in their learning, self-organizing,
and processing dynamics. They are perfectly suited to deal with complex
amplitude, composed of amplitude and phase, which is one of the core concepts
in physical systems dealing with electromagnetic, light, sonic/ultrasonic, and
quantum waves (electron and superconducting waves). This, together with the
widespread use of analytic signals, gives them a critical advantage in
practical applications in diverse fields of engineering, where signals are
routinely analyzed and processed in time/space, frequency, and phase domains.
In addition, broad-sense CVNNs such as quaternion and Clifford neural networks,
as well as kernel and reservoir approaches, underpin unique new directions in
color-information treatment, robotics and control. To further promote
research activities in this area, IEEE Transactions on Neural Networks plans to
publish a Special Issue on "Complex- and hypercomplex-valued neural
networks" to be published in January 2014.
We welcome theoretical papers,
application papers, as well as survey papers. Topics include, but are not
limited to:
·Theoretical
aspects of CVNNs such as complex-valued activation functions, gradient, and
stability
·Learning/Self-organization
algorithms and processing dynamics in CVNNs
·Chaos in
the complex domain, coherence, and causality
·Complex-valued associative memories and
attractor networks
·Feedforward/Recurrent CVNNs for time series analysis and
classification
·Phase-only
and phase-sensitive signal processing and nonlinear filtering using CVNNs
·Distributed,
widely linear, sparse, and kernel CVNN approaches
·Pattern
recognition, classification and time series prediction using CVNNs
·Applications
of CVNNs in image processing, speech processing and bioinformatics
·Frequency-
, time-frequency, and spatio-temporal domain CVNN processing
·Quantum
computation and quantum neural networks
·CVNNs for
trajectory tracking, robotics and control
·Clifford,
quaternion, and multidimensional neural networks
Important
Dates:
January 15
2013 JANUARY
31 2013 – Extended deadline for manuscript submission
August 15 2013 – Notification to authors
September 15 2013 – Deadline
for submission of revised manuscripts
October 1 2013 – Final decision
January 2014 – Special
issue
publication
in the IEEE TNNLS
Guest Editors
Akira Hirose, The University of
Tokyo, Japan, e-mail: ahirose “at” ee.t.u-tokyo.ac.jp
Igor Aizenberg, Texas A&M
University - Texarcana, U.S.A., e-mail: Igor.Aizenberg “at” tamut.edu
Danilo P. Mandic, Imperial College, U.K.,
e-mail: d.mandic “at” imperial.ac.uk
Submission
Instructions
1. Read the information for Authors at
http://cis.ieee.org/publications.html
2. Submit the manuscript by January
15, 2013 January 31, 2013at
the IEEE-TNNLS webpage http://mc.manuscriptcentral.com/tnnls and follow the submission procedure.
Please, clearly indicate on the first page of the manuscript and the Author's
Cover Letter that the manuscript has been submitted to the Special Issue on Complex-
and Hypercomplex-Valued Neual
Networks. Send also an
email to the guest editors to notify of your submission.