<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class="">----------------We apologize if you receive this message several times--------- </div><div class=""><br class=""></div><div class="">Call for papers ICPR’2020 Workshop. </div><div class="">WS GOES ONLINE. THE SUBMISSION DEAD-LINE IS Extended October 17!</div><div class=""><br class=""></div><div class="">**************************Explainable Deep Learning/AI********************</div><div class=""><a href="https://edl-ai-icpr.labri.fr/" class="">https://edl-ai-icpr.labri.fr/</a></div><div class="">Date: January 11th 2021</div><div class=""><br class=""></div><div class="">THE SUBMISSION DEADLINE IS EXTENDED OCTOBER 17th</div><div class=""><br class=""></div><div class="">The recent focus of AI and Pattern Recognition communities on the supervised learning </div><div class="">approaches, and particularly to Deep Learning / AI, resulted in considerable increase of </div><div class="">performance of Pattern Recognition and AI systems, </div><div class="">but also raised the question of the trustfulness and explainability of their predictions </div><div class="">for decision-making. </div><div class="">Instead of developing and using Deep NNs as black boxes and adapting known architectures </div><div class="">to variety of problems, the goal of explainable Deep Learning / AI is to propose methods </div><div class="">to “understand” and “explain” how the these systems produce their decisions. </div><div class="">The goals of the workshop are to bring together research community which is working on </div><div class="">the question of improving explainability of AI and Pattern Recognition algorithms and systems. </div><div class="">The topics of the workshop cover but are not limited to:</div><div class=""><br class=""></div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>“Sensing” or “salient features” of Neural Networks and AI systems - explanation of </div><div class="">which features for a given configuration yield predictions both in spatial (images) and </div><div class="">temporal (time-series, video) data;</div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>Attention mechanisms in Deep Neural Networks and their explanation;</div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>For temporal data, the explanation of which features and at what time are the most </div><div class=""> prominent for the prediction and what are the time intervals when the contribution </div><div class=""> of each data is important; </div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>How the explanation can help on making Deep learning architectures more sparse </div><div class=""> (pruning) and light-weight;</div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>When using multimodal data how the prediction in data streams are correlated and </div><div class=""> explain each other;</div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>Automatic generation of explanations / justifications of algorithms and systems’ </div><div class=""> decisions;</div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>Decisional uncertainly and explicability </div><div class="">•<span class="Apple-tab-span" style="white-space:pre"> </span>Evaluation of the explanations generated by Deep Learning and other AI systems.</div><div class=""><br class=""></div><div class="">*** Pannel: </div><div class="">“Toward more explainable Deep Learning and AI systems”, Chair: Dragutin Petcovic(SFSU,USA)</div><div class="">Moderator will ask invited speakers to briefly present their opinions and ideas on </div><div class="">the topic of the panel and then the audience will be invited to a discussion</div><div class=""><br class=""></div><div class="">*** Important Dates:</div><div class=""><br class=""></div><div class=""> Submission deadline EXTENDED (Hard deadline): October 17th 2020</div><div class=""> Workshop author notification: November 10th 2020</div><div class=""> Camera-ready submission: November 15th 2020</div><div class=""> Finalized workshop program: December 1st 2020</div><div class=""><br class=""></div><div class="">*** Paper Submission:</div><div class=""><br class=""></div><div class="">The Proceedings of the EDL-AI 2020 workshop will be published in the Springer </div><div class="">Lecture Notes in Computer Science (LNCS) series. Papers will be selected by a single blind</div><div class="">(reviewers are anonymous) review process. Submissions must be formatted in accordance </div><div class="">with the Springer's Computer Science Proceedings guidelines. Two types of contribution </div><div class="">will be considered:</div><div class=""><br class=""></div><div class=""> Full paper (12-15 pages)</div><div class=""> Short papers (6-8 pages)</div><div class=""><br class=""></div><div class="">*** Submission site: is Open <a href="https://edl-ai-icpr.labri.fr" class="">https://edl-ai-icpr.labri.fr</a></div><div class=""><br class=""></div><div class="">Program Committee: </div><div class=""><br class=""></div><div class="">Christophe Garcia (LIRIS, France) </div><div class="">Hugues Talbot (EC, France) </div><div class="">Dragutin Petkovic (SFSU,USA) </div><div class="">Alexandre Benoît( LISTIC,France) </div><div class="">Mark T. Keane (UCD, Ireland)</div><div class="">Georges Quenot(LIG, France) </div><div class="">Stefanos Kolias (NTUA, Grece) </div><div class="">Jenny Benois-Pineau(LABRI, France)</div><div class="">Hervé Le Borgne (LIST, France)</div><div class="">Noel O’Connor (DCU, Ireland)</div><div class="">Nicolas Thome(CNAM, France)</div><div class=""><br class=""></div><div class="">Due to COVID situation, the WorkShop Will be in ONLINE "live" Format. </div><div class="">ALL ACCEPTED PAPERS WILL BE PUBLISHED. </div><div class=""><br class=""></div><div class=""><br class=""></div><div class="">Jenny Benois-Pineau, Georges Quenot</div><div class="">Workshop Organizers</div><div class="">
<div style="color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">Jenny Benois-Pineau, <br class="">Professeure en Informatique, <br class="">Chargée de mission aux relations Internationales<br class="">Collège Sciences et Technologies, <br class="">Université de Bordeaux</div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">351, crs de la Libération</div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">33405 Talence</div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">France</div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">tel.: +33 (0) 5 40 00 84 24<br class=""><br class="">Jenny Benois-Pineau, PhD, HDR, <br class="">Professor of Computer Science, <br class="">Chair of International relations<br class="">School of Sciences and Technologies<br class="">University of Bordeaux </div><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">351, crs de la Libération<br class="">33405 Talence<br class="">tel.: +33 (0) 5 40 00 84 24</div></div>
</div>
<br class=""></body></html>