<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div>
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span style="color: rgb(0, 0, 0); font-family: Calibri, Helvetica, sans-serif; font-size: 12pt;">--- (Apologies for cross-posting; please pass along to any colleagues and students you think may be interested.) ---</span><br>
</div>
<div dir="ltr">
<div style="font-family:Calibri,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
SPECIAL SESSION ON
<div>“Human-in-the-loop Learning System and its User-centric Methods”</div>
<div>The 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2021)</div>
<div>October 17-20, 2021 – Melbourne, Australia</div>
<div> (Code jgrt6) </div>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm; text-align:justify; text-justify:inter-ideograph">
<b><span lang="EN-GB" style="color:black">DEADLINES </span></b></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm; text-align:justify; text-justify:inter-ideograph">
<span lang="EN-GB" style="color:black">April 5, 2021: deadline for paper submission </span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black">May 26, 2021: notification of paper acceptance/rejection </span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black">July 12, 2021: deadline for final camera-ready papers. </span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black"><br>
</span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black"><br>
</span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black"><br>
</span></p>
<p class="x_MsoNormal" style="margin-top: 0px; margin-bottom: 0px;margin:0cm 0cm 10pt; line-height:115%; font-size:11pt; font-family:Calibri,sans-serif; margin-bottom:0cm">
<span lang="EN-GB" style="color:black">Session Organizers:</span></p>
<div>Dr. Junpei Zhong </div>
<div>Prof. Ahmad Lotfi </div>
<div>Dr. David Ada Adama</div>
<div>Dr. Weihong Chin </div>
<div><br>
</div>
<div>Session area: </div>
<div>Human-Machine Systems</div>
<div><br>
</div>
<div>Session description: </div>
<div>Human-in-the-Loop (HIL) means including human feedback into the training loop of the machine learning models to improve the quality of training and to augment the functions of the model. The key research problems in algorithms are how we can evaluate
the uncertainty of a model’s prediction? How to leverage both active learning from a human and the optimization of the models? When we use hierarchical reinforcement learning, how can we achieve the goals when the reward is sparse? In sum, we should find an
optimal solution to the trade-off between the model’s accuracy and efficiency in designing the HIL algorithms.
</div>
<div><br>
</div>
<div>Apart from the algorithm design, another key issue in HIL research is from a user-centric perspective, in both data collection and model evaluation steps. Since the quality of the training datasets is also extremely important, how to integrate multi-modal
data from the users with different sensing techniques, such as smart gloves made by flexible sensors, portable eye-trackers, portable brain imaging techniques, is another problem. How can we design the users’ subjective evaluation based on multi-modal signals?
Furthermore, proper designs the interaction between machines and human could also relate to HCI and UX/UI fields etc.
</div>
<div><br>
</div>
<div>This special session is a follow-up session of “HIL machine learning and its applications” in SMC2020. We offer an opportunity for researchers and practitioners in diverse fields from machine learning, robotics, designers or end-users to join the discussion.</div>
<div><br>
</div>
<div>A selection of the accepted papers is welcomed to submit their extended versions to a special issue of a journal we edit later this year, subject to rigorous peer review.
</div>
<div><br>
</div>
<div>Topics of interest include, but are not limited to:</div>
<div><br>
</div>
<div>• Human-Centric Design for Robots or other Intelligent Devices</div>
<div>• Human Guided Reinforcement Learning</div>
<div>• Human-robot Collaboration</div>
<div>• Human-robot Social Interaction</div>
<div>• Dialogue Systems with Human-in-the-loop</div>
<div>• Interpretable Machine Learning with Human-in-the-loop</div>
<div>• Active Learning and Continuous Learning</div>
<div>• Learning by Demonstration</div>
<div>• Human Factors in HCI/HRI</div>
<div>• etc.</div>
<div><br>
</div>
<div><br>
</div>
<div><br>
</div>
<div>SUBMISSION</div>
<div>Papers must be submitted electronically for peer review through PaperCept by April 5, 2021: https://conf.papercept.net/conferences/scripts/start.pl. In PaperCept, click on the SMC 2021 link “Submit a contribution to SMC 2021” and follow the steps. (Code
jgrt6)</div>
<div>All papers must be written in English and should describe the original work. For guidelines, please follow the SMC website link http://ieeesmc2021.org/call-for-papers/</div>
<div><br>
</div>
<div>DEADLINES</div>
<div>April 5, 2021: deadline for paper submission</div>
<div>May 26, 2021: notification of paper acceptance/rejection</div>
<div>July 12, 2021: deadline for final camera-ready papers.</div>
<br>
<p style="margin-top: 0px; margin-bottom: 0px;"></p>
<br>
</div>
</div>
</div>
</body>
</html>