<div dir="ltr"><span id="docs-internal-guid-295f508e-8d1d-0601-06cc-9c07a23e0bbc"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Dear Colleagues,</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">In addition to our three exciting challenges, we have prepared a very innovative ECML-PKDD 2016 discovery challenge, which collocates in the realm of Automatic Network Management. </span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">This challenge is one of the first explorations of ML for automatic network analysis. Our goal is to promote the use of ML for network-related tasks in general and, at the same time, to assess the participants' ability to quickly build a learning-based system showing a reliable performance.  </span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Please see more information at</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><a href="http://www.neteye-blog.com/netcla-the-ecml-pkdd-network-classification-challenge/" style="text-decoration:none"><span style="font-size:12.6667px;font-family:Arial;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">http://www.neteye-blog.com/netcla-the-ecml-pkdd-network-classification-challenge/</span></a></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Schedule</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Aug.  12: the challenge starts, registration opens</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Sept.  7: test data released, submission page opens</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Sept. 10: submissions due</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Sept. 12: Results and Paper invitations</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Sept. 23: ECML-PKDD challenge track</span></p><br><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">The schedule is tight but we have encoded the network data using simple feature vectors for learning a multi-class, single label, classification task. Thus, you can simply try your own multiclass classification algorithms and watch if they improve on strong baselines.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">The aim is to find out which ML algorithms can better deal with this kind of data.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Best,</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Alessandro and Elio</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:12.6667px;font-family:Arial;vertical-align:baseline;white-space:pre-wrap">Discovery Challenge Chairs of ECML-PKDD 2016 </span></p><br></span></div>