<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class=""><span class="" style="font-size: 14px; orphans: 2; widows: 2;">UNIVERSITY OF CHICAGO</span><br class="" style="font-size: 14px; orphans: 2; widows: 2;"><span class="" style="font-size: 14px; orphans: 2; widows: 2;">DEPARTMENT OF COMPUTER SCIENCE</span></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;">PRESENTS</span></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;"><br class=""></span></div><div class="" style="orphans: 2; widows: 2;"><div class="" style="margin: 0px; line-height: normal;"><img apple-inline="yes" id="37F0A660-F3AD-4E5B-B167-959457218932" height="116" width="116" apple-width="yes" apple-height="yes" src="cid:B06CFE00-29C4-4F4E-88CD-E2DC9DECC792@cs.uchicago.edu" class=""></div></div><div class="" style="orphans: 2; widows: 2;"><div class="" style="margin: 0in 0in 0.0001pt;"><b class="" style="font-size: 14px;"><br class=""></b></div><div class="" style="margin: 0in 0in 0.0001pt;"><b class="" style="font-size: 14px;">Gao Huang</b></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class=""><span class=""><span class="" style="font-size: 14px;"><i class="">Cornell University</i></span></span></span></div><div class="" style="margin: 0in 0in 0.0001pt;"><br class=""></div><div class="" style="margin: 0in 0in 0.0001pt;"><b class=""><font class="" style="font-size: 14px;"><br class=""></font></b></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 14px;"><b class=""><font class="">Wednesday, February 28, 2018 at 2:30 pm <br class="">Ryerson 251</font></b><br class=""></span></div></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;"><br class=""></span></div><div class=""><br class=""></div><div class=""><div class=""><b class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">Title: </b><span class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">On the Redundancy in Deep Learning</span></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class=""><br class=""></b></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class="">Abstract:</b></div><div class=""><font color="#212121" face="Roboto, Helvetica, Arial, sans-serif" class=""><span class=""><span class=""><span class=""><span class="" style="font-size: 14px;">As one of the most popular techniques in artificial intelligence, deep learning has been widely used for computer vision, natural language processing, robotics, etc. On specific tasks, it has achieved or even surpassed human-level performance. However, the strong generalization ability of deep learning is still not well understood by the community. Why can such over-parameterized neural networks generalize well?<br class=""><br class="">In this talk, I will show that deep networks have considerable redundancy - although they are parameterized by millions of parameters, they may not use them effectively. I will first introduce a simple algorithm that reveals the parameter redundancy in deep residual networks and show that redundancy indeed helps improving generalization. From the practical viewpoint, redundancy is problematic as it increases computational cost. I will then present a novel network architecture that has less redundancy yet with strong generalization ability. Finally, I will introduce an adaptive evaluation method that reduces redundant computation for each individual sample.<br class=""> </span></span><span class="" style="font-size: 14px;"> </span></span></span><br class=""></font><b class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">Bio:</b></div><div class=""><span id="docs-internal-guid-8bdccc40-716c-e22d-6a5f-d3d1c5863489" class="" style="font-size: 14px; white-space: pre-wrap;"><div class="" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><font color="#212529" class=""><i class="">Gao Huang is a postdoctoral researcher in the Department of Computer Science at Cornell University, where he works on deep learning and computer vision with Professor Kilian Weinberger. Before joining Cornell, he did his PhD at Tsinghua University. His work on DenseNet won the Best Paper Award at CVPR 2017.</i></font></div><div class="" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><font color="#212529" class=""><i class=""><br class=""></i></font></div></span></div><div class=""><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class="">Host: Risi Kondor</b></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><br class=""></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><i class=""><font size="2" class="">Refreshments served after the talk in Ry. 255</font></i></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><i class=""><font size="2" class=""><br class=""></font></i></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><i class=""><font size="2" class="">Link to PDF: </font></i><a href="https://www.cs.uchicago.edu/sites/cs/files/uploads/seminar_announcements/Huang poster.pdf" class="">https://www.cs.uchicago.edu/sites/cs/files/uploads/seminar_announcements/Huang%20poster.pdf</a></div></div></div></body></html>