<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);">
<p style="margin-right: 0cm; margin-left: 0cm; font-size: 12pt; font-family: 宋体;margin:0cm;margin-bottom:.0001pt">
<span lang="EN-US" style="font-size:
10.5pt;mso-bidi-font-size:11.0pt;font-family:等线;mso-ascii-theme-font:minor-latin;
mso-fareast-theme-font:minor-fareast;mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Times New Roman";mso-bidi-theme-font:minor-bidi"></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">CFP: SMC 2020 Special Session: Human-in-the-loop Machine Learning and Its Applications</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><br>
</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Link: <a href="https://jonizhong.weebly.com/smc2020.html">https://jonizhong.weebly.com/smc2020.html</a></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Toronto, Canada, OCT 11-14, 2020</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Deadline: April 30, 2020</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">==COVID-19 UPDATE==</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">We will be closely following the update of COVID-19 and organizing plan of SMC 2020.
</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Dear all,</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">We would like to cordially invite you to submit a paper for the Special Session “Human-in-the-loop Machine Learning and Its Applications” in the<span style="mso-spacerun:yes">
</span>IEEE International Conference on Systems, Man, and Cybernetics 2020, held on Oct 11-14, 2020, in Toronto Canada.
</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Human-in-the-Loop (HIL) means including human feedback into the training loop of the machine learning models in order to facilitate the following requirements:</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">1) to improve the quality of training and reduce/prevent the error of the model. When the testing error is larger than a certain threshold, the HIL learning model
is able to obtain the new data-points from the users in an interactive way. </span>
</p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">2) to incorporate the human user labelling to improve the pre-trained models.<span style="mso-spacerun:yes">
</span>During the training of the state-of-the-art models, the quality of the training data-sets is extremely important. One solution to actively incorporate more data is optimizing the models by including the human users’ feedback (e.g. rewards in RL) or new
data-points (e.g. supervised learning) to adapt the pre-trained models in different environments.</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><span style="mso-spacerun:yes"> </span></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">In the aforementioned requirements, humans are involved in the training process of the algorithms by continuously optimizing the model’s parameters, feeding the data
or even adjusting the model itself by meta-learning. From the perspective of algorithm design, a key problem to design a proper training with a human in the loop is how to leverage both active learning from a human and the optimization of the models. In other
words, how can we design a proper query strategy depending on different applications and scenarios?</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><span style="mso-spacerun:yes"> </span></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">When properly implemented, the HIL is suitable to be applied in real-world applications where the data is sparse. The active learning mechanism built in the model
can be helpful which could seek the human’s help in a form of supervised or reinforcement learning.<span style="mso-spacerun:yes">
</span>In this way, proper designs of interactive displays, machines and robots could be of help to obtain the human’s inputs.
</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Specifically, we are particularly encouraging robotic applications and their experimental deployment using HIL algorithms. We believe that the HIL algorithms will
be an effective method to make robotic platforms more adaptive and safer to interact with. The workshop will offer the opportunity for researchers and practitioners in the diverse field where human reinforcement feedback would have a positive impact on the
training processes.<span style="mso-spacerun:yes"> </span>The inclusion of HIL would allow robots and machine learning models to use both internal and external feedback to speed up the learning process and also improve its performance.<span style="mso-spacerun:yes">
</span>In many ways, this could allow the models to learn through their own self-reflection as well as the external input from a human.<span style="mso-spacerun:yes">
</span></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><span style="mso-spacerun:yes"> </span></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Topics of interest include, but are not limited to:</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Human Guided Reinforcement Learning;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Human-robot Collaboration;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Human-robot Social Interaction;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Dialogue Systems with Human-in-the-loop;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Interpretable Machine Learning with Human-in-the-loop;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Active Learning and Continuous Learning;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Learning by Demonstration;</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Human Factors in HCI/HRI, etc.</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Important Dates:</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">-<span style="mso-tab-count:1">
</span>Deadline for Submission: April 30, 2020</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">-<span style="mso-tab-count:1">
</span>Acceptance Notification: May 10, 2020</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">-<span style="mso-tab-count:1">
</span>Conference Dates: Oct 11-14, 2020.</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Organizers:</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Joni Zhong,<span style="mso-spacerun:yes">
</span>Nottingham Trent University, UK</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Mark Elshaw, Coventry University, UK</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Yanan Li, University of Sussex, UK</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Stefan Wermter, University of Hamburg, Germany</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US">Xiaofeng Liu, Hohai University, China</span></p>
<p style="margin: 0cm 0cm 0.0001pt; text-align: justify; font-size: 10.5pt"><span lang="EN-US"><o:p> </o:p></span></p>
<br>
</div>
</body>
</html>