<div dir="ltr"><div class="gmail_quote"><div dir="ltr"><b>TL;DR – CFP</b>: Neural Networks journal special issue on GANs<br>
<b>GUEST EDITORS</b>: <font size="2">Ariel Ruiz-Garcia, Jürgen Schmidhuber, Vasile Palade, Clive Cheong Took, Danilo Mandic</font><br>
<b>SUBMISSION DEADLINE</b>: 30th September 2019 <br>
----------------------------------<br><div id="m_-978178437002378006:1cv" class="m_-978178437002378006a3s m_-978178437002378006aXjCH">
<br>
<b>CALL FOR PAPERS</b>: Neural Networks Journal <br>
<br>
<font size="4"> <span style="color:rgb(7,55,99)"><b>Special Issue on Deep Neural Network Representation and Generative Adversarial Learning</b></span></font><br>
<br>
Generative Adversarial Networks (GANs) have proven to be efficient
systems for data generation. Their success is achieved by exploiting a
minimax learning concept, which has proved to be an effective paradigm
in earlier works, such as predictability minimization, in which two
networks compete with each other during the learning process. One of the
main advantages of GANs over other deep learning methods is their
ability to generate new data from noise, as well as their ability to
virtually imitate any data distribution. However, generating realistic
data using GANs remains a challenge, particularly when specific features
are required; for example, constraining the latent aggregate
distribution space does not guarantee that the generator will produce an
image with a specific attribute. On the other hand, new advancements in
deep representation learning (RL) can help improve the learning process
in Generative Adversarial Learning (GAL). For instance, RL can help
address issues such as dataset bias and network co-adaptation, and
identify a set of features that are best suited for a given task.<br>
<br>
Despite their obvious advantages and their application to a wide range
of domains, GANs have yet to overcome several challenges. They often
fail to converge and are very sensitive to parameter and hyper-parameter
initialization. Simultaneous learning of a generator and a
discriminator network often results in overfitting. Moreover, the
generator model is prone to mode collapse, which results in failure to
generate data with several variations. Accordingly, new theoretical
methods in deep RL and GAL are required to improve the learning process
and generalization performance of GANs, as well as to yield new insights
into how GANs learn data distributions.<br>
<br>
This special issue on Deep Neural Network Representation and Generative
Adversarial Learning invites researchers and practitioners to present
novel contributions addressing theoretical and practical aspects of deep
representation and generative adversarial learning. The special issue
will feature a collection of high quality theoretical articles for
improving the learning process and the generalization of generative
neural networks. State-of-the-art applications based on deep generative
adversarial networks are also very welcome. Topics of interest for this
special issue include, but are not limited to:<br>
<br>
Representation learning methods and theory;<br>
Adversarial representation learning for domain adaptation;<br>
Network interpretability in adversarial learning;<br>
Adversarial feature learning;<br>
RL and GAL for data augmentation and class imbalance;<br>
New GAN models and new GAN learning criteria;<br>
RL and GAL in classification;<br>
Adversarial reinforcement learning;<br>
GANs for noise reduction;<br>
Recurrent GAN models;<br>
GANs for imitation learning;<br>
GANs for image segmentation and image completion;<br>
GANs for image super-resolution;<br>
GANs for speech and audio processing<br>
GANs for object detection;<br>
GANs for Internet of Things;<br>
RL and GANs for image and video synthesis;<br>
RL and GANs for speech and audio synthesis;<br>
RL and GANs for text to audio or text to image synthesis;<br>
RL and GANs for inpainting and sketch to image;<br>
RL and GAL in neural machine translation;<br>
RL and GANs in other application domains. <br>
<br>
<b>Important Dates:</b><br>
<br>
30 September 2019 – Submission deadline <br>
31 December 2019 – First decision notification<br>
28 February 2020 – Revised version deadline<br>
30 April 2020 – Final decision notification<br>
July 2020 – Publication<br>
<br>
<b>Guest Editors:</b><br>
<br>
Dr Ariel Ruiz-Garcia<br>
Coventry University, UK<br>
Email: <a href="mailto:ariel.9arcia@gmail.com" target="_blank">ariel.9arcia@gmail.com</a><br>
<br>
Professor Jürgen Schmidhuber<br>
NNAISENSE,<br>
Swiss AI Lab IDSIA,<br>
USI & SUPSI, Switzerland<br>
Email: <a href="mailto:juergen@idsia.ch" target="_blank">juergen@idsia.ch</a><br>
<br>
Dr Vasile Palade<br>
Coventry University, UK<br>
Email: <a href="mailto:vasile.palade@coventry.ac.uk" target="_blank">vasile.palade@coventry.ac.uk</a><br>
<br>
Dr Clive Cheong Took<br>
Royal Holloway (University of London), UK<br>
Email: <a href="mailto:Clive.CheongTook@rhul.ac.uk" target="_blank">Clive.CheongTook@rhul.ac.uk</a><br>
<br>
Professor Danilo Mandic<br>
Imperial College London, UK<br>
Email: <a href="mailto:d.mandic@imperial.ac.uk" target="_blank">d.mandic@imperial.ac.uk</a><br>
<br>
<b>Submission Procedure:</b><br>
<br>
Prospective authors should follow the standard author instructions for Neural Networks, and submit manuscripts online at <a href="http://ees.elsevier.com/neunet/" rel="noreferrer" target="_blank">http://ees.elsevier.com/neunet/</a>.
Authors should select “VSI:RL and GANs” when they reach the “Article
Type” step and the "Request Editor" step in the submission process.<br>
<br>
For any questions related to the special issue please email Dr Ariel Ruiz-Garcia (<a href="mailto:ariel.9arcia@gmail.com" target="_blank">ariel.9arcia@gmail.com</a>)<div class="m_-978178437002378006yj6qo m_-978178437002378006ajU"><div id="m_-978178437002378006:p8" class="m_-978178437002378006ajR"><img class="m_-978178437002378006ajT" src="https://ssl.gstatic.com/ui/v1/icons/mail/images/cleardot.gif"><br>
</div></div></div></div></div></div>