<div dir="ltr"><div class="gmail_quote"><br><div lang="EN-US" link="#0563C1" vlink="#954F72"><div class="m_-6656062058359812353WordSection1"><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black"><img width="1017" height="115" style="width:10.5937in;height:1.1979in" id="m_-6656062058359812353Picture_x0020_1" src="cid:image001.jpg@01D3A3DE.7CF4C6C0" alt="cid:image001.jpg@01D3A3DE.7CF4C6C0"></span><span style="font-family:"Verdana",sans-serif;color:black"><u></u><u></u></span></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black">DATE:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black"> </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">Friday, March 16, 2018</span></b><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black">TITLE:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black">  </span><b><span style="font-size:20.0pt;font-family:"Verdana",sans-serif">Deep Learning with Induced Priors<u></u><u></u></span></b></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black">TIME:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black"> </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">3<span style="color:black">:30PM</span></span></b><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black">LOCATION:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> <b> </b></span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">GMCS 314</span></b><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black">SPEAKER:</span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black">  </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">Saining Xie</span></b> <b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">, Doctoral Student<span style="color:#1f497d"><br></span>Computer Science, UCSD</span></b><u></u><u></u></p><p class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal"><span style="font-family:"Verdana",sans-serif;color:black">ABSTRACT:</span><u></u><u></u></p><h2><span class="m_-6656062058359812353event-description"><span style="font-size:11.0pt;font-family:"Verdana",sans-serif;font-weight:normal">Deep learning has reshaped the landscape of research and applications in artificial intelligence. In contrast to traditional hand-crafted feature engineering, and with the support of big-data and big-compute, the promise and dominant paradigm of deep learning research is supervised, end-to-end and automatic representation learning. However, to tackle many real world problems, smart structural design decisions have to be made, oftentimes through induced priors. Those priors can be hard-wired, or automatically learned from the data or environment. In this talk I will introduce my research in designing and utilizing deep learning structures for different application scenarios in supervised learning and reinforcement learning. In particular, I will talk about my recent work on induced priors and structures for 3D point cloud recognition and transfer learning for continuous control.<u></u><u></u></span></span></h2><h2><span style="font-size:11.0pt;font-family:"Verdana",sans-serif;color:black;font-weight:normal">HOST:</span><span style="font-family:"Verdana",sans-serif;color:#1f497d">  </span><span class="m_-6656062058359812353event-description"><span style="font-size:12.0pt;font-family:"Verdana",sans-serif;font-weight:normal">Xiaobai Liu</span></span><u></u><u></u></h2><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><span style="font-size:9.5pt;font-family:"Verdana",sans-serif;color:black"> </span><u></u><u></u></p><p class="MsoNormal"> <u></u><u></u></p><p class="MsoNormal"><span style="font-size:9.5pt;font-family:"Verdana",sans-serif;color:black">Dr. Jose E. Castillo<br>Director/Professor<br>Computational Science Research Center<br>5500 Campanile Drive<br>San Diego State University<br>San Diego, CA  92182-1245<br>(619) 59407205/3430, FAX </span><a href="tel:%28619%29%20594-2459" target="_blank"><span style="font-size:9.5pt;font-family:"Verdana",sans-serif">(619) 594-2459</span></a><u></u><u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><u></u> <u></u></p></div></div><br>______________________________<wbr>_________________<br>
SDSU Computational Science Research Center<br>
Mailing List<br></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature">







<p>Jose E. Castillo  Ph.D.</p><p>Director / Professor </p>
<p>Computational Science Research Center</p>
<p>5500 Campanile Dr</p>
<p>San Diego State University</p>
<p>San Diego CA 92182-1245</p>
<p>619 5947205/3430, Fax 619-594-2459</p><p> <a href="http://www.csrc.sdsu.edu/mimetic-book/" target="_blank">http://www.csrc.sdsu.edu/mimetic-book/</a></p></div>
</div>