<div dir="ltr"><span class="gmail-im"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" id="gmail-m_-3424256783368247622gmail-m_7078047141215549601m_-1398293863336053597gmail-docs-internal-guid-d8ddf604-5463-eeae-68b0-d06c53d4186f"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">CALL FOR CONTRIBUTIONS</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">The ICML/IJCAI-ECAI 2018 <span class="gmail-il">Workshop</span> on Automatic Machine Learning (<span class="gmail-il">AutoML</span> 2018)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Collocated with the Federated AI Meeting (including ICML, IJCAI, AAMAS, and ICCBR) in Stockholm, July 13, 14, or 15 (TBD), 2018</span></p></span><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Web: </span><a href="http://icml2018.automl.org" style="text-decoration:none" target="_blank"><span style="font-size:10pt;font-family:Arial;color:rgb(17,85,204);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">http://icml2018.<span class="gmail-il">automl</span>.org</span></a></p><div><div class="gmail-adm"><div id="gmail-q_16261542149bd77c_3" class="gmail-ajR gmail-h4"><div class="gmail-ajT"></div></div></div><div class="gmail-im"><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">------------------------------<wbr>------------------------------<wbr>----</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><b><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Important Dates:</span></b></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> Submission deadline: 23 May 2018, 11:59pm UTC-12 (May 23 anywhere in the world)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> Notification: 9 June 2018</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">------------------------------<wbr>------------------------------<wbr>----</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-il">Workshop</span> topic:</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><img src="https://lh5.googleusercontent.com/e2UGQS5JW7pYoz14ZFR02S25L5lUe6OWBvbClHhEpJFifnlRF9SoIYi_ebEVpNNUen2CB2U3BEVQy1TFVgDy2DBFXGgpjggWJV1-7f_uH3AjHIpAnZ-GYf7TWZYfC327eo8f__Jj" style="border-color: currentcolor; border-style: none; border-width: medium;" class="gmail-m_-3424256783368247622gmail-CToWUd gmail-CToWUd" width="1" height="1"></span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Machine learning has been very successful, but its successes rely on human machine learning experts to define the learning problem, select, collect and preprocess the training data, choose appropriate <span class="gmail-il">ML</span> architectures (deep learning, random forests, SVMs, etc) and their hyperparameters, and finally evaluate the suitability of the learned models for deployment. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that are more bullet-proof and can be used easily without expert knowledge. We call the resulting research area that targets progressive automation of machine learning <span class="gmail-il">AutoML</span>.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-il">AutoML</span> aims to automate many different stages of the machine learning process, and encourages contributions in any of the following (or related) areas:</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Model selection, hyper-parameter optimization, and model search</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Neural architecture search</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Meta learning and transfer learning</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic feature extraction / construction</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Demonstrations (demos) of working <span class="gmail-il">AutoML</span> systems</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic generation of workflows / workflow reuse</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic problem "ingestion" (from raw data and miscellaneous formats)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic feature transformation to match algorithm requirements</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic detection and handling of skewed data and/or missing values</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic acquisition of new data (active learning, experimental design)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic report writing (providing insight on automatic data analysis)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic selection of evaluation metrics / validation procedures</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic selection of algorithms under time/space/power constraints</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic prediction post-processing and calibration</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic leakage detection</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- Automatic inference and differentiation</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- User interfaces and human-in-the-loop approaches for <span class="gmail-il">AutoML</span></span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">We especially encourage demos of working <span class="gmail-il">AutoML</span> systems; demo proposals are submitted through an accompanying paper. The best 2-3 papers will be invited for oral plenary presentation. All other accepted papers will be presented as posters and short poster spotlight presentations. </span></p></div></div><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">For submission details please see</span><a href="http://icml2018.automl.org" style="text-decoration:none" target="_blank"> http://icml2018.<span class="gmail-il">automl</span>.org</a><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">.</span></p><br><div><div><div><div class="gmail-adL"><span class="gmail-im"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Confirmed Invited speakers:</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- <span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Chelsea Finn</span></span></span></span></span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- <span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Yolanda Gil </span></span><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"></span></span></span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- <span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Luc de Raedt </span></span></span></span></span></span></span></span><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"></span></span></span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">- <span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><span class="gmail-im"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Ameet Talwalkar </span></span></span></span></span></p><br><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Chairs: Roman Garnett, Frank Hutter, Joaquin Vanschoren</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Organizing committee: Pavel Brazdil, Christophe Giraud-Carrier, Isabelle Guyon</span></p></span></div></div></div></div></div>