<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Wingdings;
panose-1:5 0 0 0 0 0 0 0 0 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
p.MsoNoSpacing, li.MsoNoSpacing, div.MsoNoSpacing
{mso-style-priority:1;
margin:0cm;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:1066218070;
mso-list-type:hybrid;
mso-list-template-ids:-1488000014 134807553 134807555 134807557 134807553 134807555 134807557 134807553 134807555 134807557;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
ol
{margin-bottom:0cm;}
ul
{margin-bottom:0cm;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-GB" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal">CFP: <o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNoSpacing"><a name="OLE_LINK19"><b><span style="font-size:12.0pt;color:#002060">Special Session on Deep and Generative Adversarial Learning<o:p></o:p></span></b></a></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK5"></a><a name="OLE_LINK6"></a><a name="OLE_LINK15"><span style="mso-bookmark:OLE_LINK6"><span style="mso-bookmark:OLE_LINK5"><span style="font-size:12.0pt;color:#002060">2019 International
Joint Conference on Neural Networks (IJCNN) </span></span></span></a></span><span style="mso-bookmark:OLE_LINK19"><span style="font-size:12.0pt;color:#002060"><o:p></o:p></span></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:12.0pt;color:#002060">July 14-19 2019,
<a name="OLE_LINK16"></a><a name="OLE_LINK17"><span style="mso-bookmark:OLE_LINK16">Budapest, Hungary</span></a><o:p></o:p></span></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"></span><a href="https://www.ijcnn.org/"><span style="mso-bookmark:OLE_LINK19">https://www.ijcnn.org/</span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19"><o:p></o:p></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><o:p> </o:p></span></p>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK3"></a><a name="OLE_LINK4"><span style="mso-bookmark:OLE_LINK3"><b>Important Dates:<o:p></o:p></b></span></a></span></p>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><span style="mso-bookmark:OLE_LINK4"><span style="mso-bookmark:OLE_LINK3"><span style="color:red">Paper submission: 15 December 2018<o:p></o:p></span></span></span></span></p>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><span style="mso-bookmark:OLE_LINK4"><span style="mso-bookmark:OLE_LINK3"><span style="color:red">Notification of acceptance: 30 January 2019
</span></span></span><span style="color:red"><o:p></o:p></span></span></p>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><b><span style="color:red"><o:p> </o:p></span></b></span></p>
<p class="MsoNormal"><span style="mso-bookmark:OLE_LINK19"><b>Aims and Scope: <o:p>
</o:p></b></span></p>
<p class="MsoNormal" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19">Deep Generative Adversarial Networks (GANs) are one of the most recent breakthroughs in deep learning (DL) and neural networks. One of the main advantages of GANs over other
deep learning systems is their ability to learn from unlabelled data, as well as their ability to generate new data from random distributions.
<a name="OLE_LINK1"></a><a name="OLE_LINK2"><span style="mso-bookmark:OLE_LINK1">However, generating realistic data using GANs remains a challenge, particularly when specific features are required; e.g., constraining the latent aggregate distribution space
does not guarantee that the generator will produce an image with a specific attribute.</span></a> New advancements in deep representation learning (RL) can help improve the learning process in GANs. For instance, RL can help address issues such as dataset
bias and network co-adaptation, and help identify a set of features that are ideal for a given task.
<o:p></o:p></span></p>
<p class="MsoNormal" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><o:p> </o:p></span></p>
<p class="MsoNormal" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK18">Practical applications of GANs include: realistic data synthesis, generation of speech or images from text, image denoising and completion, artificial
environment generation for reinforcement learning problems, conversion of satellite images into maps, class imbalance learning, or other unsupervised and supervised learning tasks. Nonetheless,</a> GANs have yet to overcome several challenges. They often fail
to converge and are very sensitive to parameter and hyperparameter initialization. Simultaneous learning of a generator and a discriminator network also makes the learning process more difficult and often results in overfitting or vanishing gradients in the
generator network. Moreover, the generator model is prone to mode collapse which results in failure to generate data with several variations. New theoretical methods in deep learning and GANs are therefore required to improve the learning process and generalization
performance of GANs. Topics of interest for this special session include, but are not limited to:<o:p></o:p></span></p>
<p class="MsoNormal" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><i><o:p> </o:p></i></span></p>
<ul style="margin-top:0cm" type="disc">
<li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Generative adversarial learning methods and theory;<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK7">Representation learning methods and theory;
<o:p></o:p></a></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19"><span style="mso-bookmark:OLE_LINK7">Adversarial representation learning for domain adaptation;
<o:p></o:p></span></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19"><span style="mso-bookmark:OLE_LINK7">Interpretable representation adversarial learning;
</span><o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Adversarial feature learning;
<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">RL and GANs for data augmentation and class imbalance;
<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">New GAN models and learning criteria;
<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">RL and GANs in classification;
<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Image completion and super-resolution;
<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK14"></a><a name="OLE_LINK10"></a><a name="OLE_LINK11"></a><a name="OLE_LINK12"></a><a name="OLE_LINK13"><span style="mso-bookmark:OLE_LINK12"><span style="mso-bookmark:OLE_LINK11"><span style="mso-bookmark:OLE_LINK10"><span style="mso-bookmark:OLE_LINK14">RL
and </span></span></span></span></a><span style="mso-bookmark:OLE_LINK14">GANs </span>
in Deep Reinforcement Learning;<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Deep learning and GANs for image and video synthesis;<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Deep Learning and GANs for speech and audio synthesis;<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19"><a name="OLE_LINK8"></a><a name="OLE_LINK9"><span style="mso-bookmark:OLE_LINK8">RL and GANs and for In-painting and Sketch to image;
</span></a><o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">Representation and Adversarial Learning in Machine Translation;<o:p></o:p></span></li><li class="MsoNoSpacing" style="mso-list:l0 level1 lfo1"><span style="mso-bookmark:OLE_LINK19">RL and GANs in other application domains.
<o:p></o:p></span></li></ul>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><b><o:p> </o:p></b></span></p>
<p class="MsoNoSpacing" style="text-align:justify"><span style="mso-bookmark:OLE_LINK19"><b>Submission:
</b>For paper guidelines please visit </span><a href="https://www.ijcnn.org/paper-submission-guidelines"><span style="mso-bookmark:OLE_LINK19">https://www.ijcnn.org/paper-submission-guidelines</span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19">
and for submissions please select Special Session <b>S06. Deep and Generative Adversarial Learning</b> as the main research topic at
</span><a href="https://ieee-cis.org/conferences/ijcnn2019/upload.php"><span style="mso-bookmark:OLE_LINK19">https://ieee-cis.org/conferences/ijcnn2019/upload.php</span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19"><span class="MsoHyperlink"><o:p></o:p></span></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><b><o:p> </o:p></b></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><b>Organizers:<o:p></o:p></b></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">Ariel Ruiz-Garcia<b>
</b>(</span></span><a href="mailto:ariel.ruiz-garcia@coventry.ac.uk"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">ariel.ruiz-garcia@coventry.ac.uk</span></span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">)
<br>
Vasile Palade<b> </b>(</span></span><a href="mailto:vasile.palade@coventry.ac.uk"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">vasile.palade@coventry.ac.uk</span></span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">)<o:p></o:p></span></span></p>
<p class="MsoNoSpacing"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">Clive Cheong Took<b>
</b>(</span></span><a href="mailto:clive.cheongtook@rhul.ac.uk"><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">clive.cheongtook@rhul.ac.uk</span></span><span style="mso-bookmark:OLE_LINK19"></span></a><span style="mso-bookmark:OLE_LINK19"><span style="font-size:10.0pt">)</span></span><span style="font-size:10.0pt"><o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<p style="line-height: 15.0pt;"><strong><span style="font-size: 13pt; font-family: 'Arial',sans-serif; color: #005eb8;">University of the Year for Student Experience<br>
</span></strong><span style="font-size: 9.0pt; font-family: 'Arial',sans-serif; color: black;">The Times and Sunday Times Good University Guide 2019</span></p>
<p style="mso-margin-top-alt: 3.0pt; margin-right: 0cm; margin-bottom: 3.0pt; margin-left: 0cm; line-height: 12.0pt;">
<strong><span style="font-size: 13pt; font-family: 'Arial',sans-serif; color: #005eb8;">2nd for Teaching Excellence</span></strong><br>
<span style="font-size: 9.0pt; font-family: 'Arial',sans-serif; color: black;">Times Higher Education UK (TEF) metrics ranking 2017 – Gold winner</span></p>
<p style="mso-margin-top-alt: 3.0pt; margin-right: 0cm; margin-bottom: 3.0pt; margin-left: 0cm; line-height: 12.0pt;">
<strong><span style="font-size: 13pt; font-family: 'Arial',sans-serif; color: #005eb8;">5th UK Student City</span></strong><br>
<span style="font-size: 9.0pt; font-family: 'Arial',sans-serif; color: black;">QS Best Student Cities Index 2018</span></p>
<p style="line-height: 15.0pt;"><strong><span style="font-size: 13pt; font-family: 'Arial',sans-serif; color: #005eb8;">13th in Guardian University Guide 2019</span></strong><br>
<span style="font-size: 9.0pt; font-family: 'Arial',sans-serif; color: black;">of 121 UK institutions ranked
</span></p>
<p style="margin-top: 15.0pt; line-height: 8.25pt;"><span style="font-size: 7.0pt; font-family: 'Arial',sans-serif;">NOTICE<br>
<br>
This message and any files transmitted with it is intended for the addressee only and may contain information that is confidential or privileged. Unauthorised use is strictly prohibited. If you are not the addressee, you should not read, copy, disclose or otherwise
use this message, except for the purpose of delivery to the addressee.<br>
<br>
Any views or opinions expressed within this e-mail are those of the author and do not necessarily represent those of Coventry University.</span></p>
</body>
</html>