<div dir="ltr"><p class="MsoNormal" align="center" style="text-align:center;line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif"><br></span></p><p class="MsoNormal" align="center" style="text-align:center;line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">AAAI-19
Workshop on Network Interpretability for Deep Learning</span></p>
<p class="MsoNormal" align="center" style="text-align:center;line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Call
for Paper</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif"> </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">This workshop aims to bring together
researchers, engineers, students in both academic and industrial communities
who concern about the interpretability of deep learning models and, more
importantly, the safety of applying these complex deep models in critical
applications such as the medical diagnosis and the autonomous driving. Efforts along this direction are expected to
open the black box of deep neural networks for better understanding and to
build more transparent deep models which are interpretable to humans. Therefore, the main theme of the workshop is
to build up consensus on the emerging topic of the network interpretability, by
clarifying the motivation, the typical methodologies, the prospective trends,
and the potential industrial applications of the network interpretability.</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif"> </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Topics of interest include but are
not limited to</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Theories of </span><span style="font-family:"Times New Roman",serif">deep<span style="color:black"> neural networks</span></span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Visualization of neural
networks</span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Diagnosing</span><span style="font-family:"Times New Roman",serif">
<span style="color:black">and</span> disentangling <span style="color:black">feature
representations of neural networks</span></span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Learning representations
for neural networks which are </span><span style="font-family:"Times New Roman",serif">interpretable, disentangled and/or
compact</span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Improving interpolation capacity of features for generative
models.</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Probabilistic logic interpretation of deep learning</span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Bridging feature
representations between visual concepts and linguistic concepts.</span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif">Safety and fairness of the deep
learning models</span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif">Industrial applications of
interpretable deep neural networks</span><span style="color:black"></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 8pt 21pt;text-align:justify;line-height:normal;border:none;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Noto Sans Symbols";color:black">●<span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:7pt;line-height:normal;font-family:"Times New Roman"">
</span></span><span style="font-family:"Times New Roman",serif;color:black">Evaluation of the
interpretability of neural networks</span><span style="color:black"></span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif"> </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Submission:</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">We are calling for the extended
abstracts with 2—4 pages and full submissions with 6—8 pages. All the accepted
papers will not be included in the proceedings of AAAI 2019, but we will
publish workshop proceedings on arXiv.org.</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif"> </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Please submit workshop papers to </span><a href="mailto:networkinterpretability@gmail.com"><span style="font-family:"Times New Roman",serif;color:rgb(5,99,193)">networkinterpretability@gmail.com</span></a><span style="font-family:"Times New Roman",serif">
.</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Submission deadline: November 5,
2018</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Notification date: November 26, 2018</span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><a name="_gjdgxs"></a><span style="font-family:"Times New Roman",serif"> </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Organizers: </span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Quanshi Zhang, <a href="mailto:zqs1022@sjtu.edu.cn">zqs1022@sjtu.edu.cn</a></span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span style="font-family:"Times New Roman",serif">Lixin Fan, <a href="mailto:lixin.fan01@gmail.com">lixin.fan01@gmail.com</a></span></p>
<p class="MsoNormal" style="line-height:normal;margin:0cm 0cm 8pt;font-size:11pt;font-family:Calibri,sans-serif"><span lang="FI" style="font-family:"Times New Roman",serif">Bolei Zhou, <a href="mailto:bzhou@csail.mit.edu">bzhou@csail.mit.edu</a></span></p></div>