<div dir="ltr"><div class="gmail_default" style="font-size:small"><div style="font-family:Arial,Helvetica,sans-serif"><font color="#000000" face="georgia, serif"><b>When:</b>         Friday, October 14th at <span style="background-color:rgb(255,255,0)"><b>12:30pm CT</b></span></font></div><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"> <br><b>Where:</b><b>  </b>     Talk will be given <font style="font-weight:bold"><u style="background-color:rgb(255,255,0)">live, in-person</u></font><font style="font-weight:bold"> </font>at</font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                       TTIC, 6045 S. Kenwood Avenue</font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                       5th Floor, Room 530<b>              </b>   </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"> </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"><b>Virtually:</b>    via Panopto (<a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=53793a5e-66c2-45cc-ac11-af2700e1817e" target="_blank">Livestream</a>) </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"><br></font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"><b>Who:</b><b> </b>           Baba C. Vemuri, University of Florida </font></p><table border="0" cellspacing="0" cellpadding="0" width="0" style="font-family:Arial,Helvetica,sans-serif;width:0in;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;border-collapse:collapse"><tbody><tr><td style="padding:0in"></td></tr></tbody></table><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"> </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><font color="#000000"><b>Title:</b><b> </b>           </font></font><span style="font-family:georgia,serif">ManifoldNet: A Deep Neural Network for Manifold-valued Data with </span><span style="font-family:georgia,serif">Applications</span></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b><br></b></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><b style="">Abstract:    </b><span style="background-color:transparent;color:rgb(0,0,0);font-size:9.9626pt;white-space:pre-wrap">Developing deep neural networks (DNNs) for manifold-valued data sets has gained significant in terest of late in the deep learning research community. Manifold-valued data abound many fields of Engineering and Sciences including but not limited to, Medical Imaging, Computer Vision, Robotics, etc., for example, diffusion tensor images (DTI), shape (landmarks) data, directional data, covariance matrices, GPS data and others. In this talk, a new theory and supporting architecture for DNNs tailored for manifold-valued data inputs dubbed, ManifoldNet, will be presented. Analogous to vector spaces where convolutions are equivalent to computing weighted means, manifold-valued data convolutions will be defined using the weighted Frechet Mean (wFM). To this end, a provably convergent recursive ´ algorithm for computation of the wFM of the given data is presented, where the weights are to be learned. Further, the proposed wFM operator is provably equivariant to the natural group actions admitted by the data manifold and achieves a contraction mapping. A novel network architecture to realize the Mani foldNet will be detailed during the talk. Experiments showcasing the performance of the ManifoldNet on regression and classification problems in Neuroimaging will be presented. Finally, if time permits, a generalization of the ManifoldNet to accommodate higher order manifold-valued convolutions will be briefly discussed. </span></font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"> </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><br></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif"><font style=""><b style="">Bio:     </b></font><span style="color:rgb(34,34,34)">Baba C. Vemuri received the PhD in Electrical and Computer Engineering from the University of Texas at Austin. Currently, he is a Distinguished University Professor in the Department of Computer and Information Sciences and Engineering and holds the Wilson and Marie Collins professorship of Engineering at the University of Florida. He holds affiliate appointments in the Department of Statistics, ECE and BME at the University of Florida. His research interests include Geometric Deep Learning, Geometric Statistics, Medical Image Computing, Computer Vision, Machine Learning and Information Geometry.</span></font></p><font face="georgia, serif"><br>For the last several years, his research work has primarily focused on statistical analysis of manifold-valued data with applications to Medical Image Computing and Computer Vision. Along this theme, he has been developing algorithms for the recursive computation of statistics on Riemannian manifolds pertinent to manifold-valued data sets e.g., diffusion magnetic resonance images (dMRI), manifold of linear subspaces (Grassmann manifold) etc. His research team has developed novel methods for 3D image segmentation, unimodal and multimodal image (rigid+nonrigid) registration, nonrigid registration of 3D point sets, metric learning, dictionary learning and large margin classifiers. He has published over 200 fully refereed articles in journals and conference proceedings on: Geometric Statistics, Medical Image Computing, Computer Vision, Graphics, and Applied Mathematics. He received the US National Science Foundation Research Initiation Award (NSF RIA) in 1988 and the Whitaker Foundation Award in 1994. He has received, several best paper awards at various International Conferences (including 3 times best poster presentation award at the biennial International Conf. on Information Processing in Medical Imaging - IPMI'01,'05 and '21), the IEEE Edward J McCluskey Technical Achievement Award (2017) for, "pioneering and sustaining contributions to Computer Vision and Medical Image Analysis." He is a Fellow of the IEEE (2001) and the ACM (2009). In 2015, he was awarded the Doctoral Dissertation Mentorship Award from the Herbert Wertheim College of Enginnering at UFL.<br><br>He served as a program chair for several conferences including the 11th IEEE International Conference on Computer Vision (ICCV 2007). He served as an area chair and a program committee member of several IEEE conferences. He was an associate editor for several journals, including the IEEE Transactions on Pattern Analysis and Machine Intelligence --TPAMI, (from 1992 to 1996), the IEEE Transactions on Medical Imaging -- TMI, (from 1997 to 2003) and the journal of Computer Vision and Image Understanding (from 2000-2010). He is currently an associate editor for the Journal of Information Geometry, Medical Image Analysis (MedIA) and is an honororay board member of the Intl. Journal of Computer Vision (IJCV).</font></div><div class="gmail_default" style="font-size:small"><br></div><div class="gmail_default" style="font-size:small"><br><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b><font color="#000000" face="georgia, serif">*********************************************************************************************</font></b></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in 0in 8pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;line-height:15.6933px"><b><font face="arial, sans-serif" color="#000000">Presence at TTIC requires being fully vaccinated for COVID-19 or having a TTIC or UChicago-approved exemption. Masks are optional in all common areas. Full visitor guidance is available at <a href="http://ttic.edu/visitors" target="_blank">ttic.edu/visitors</a>.</font></b></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in 0in 12pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial;line-height:15.6933px"><b><font face="arial, sans-serif" color="#000000">*********************************************************************************************</font></b></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b><i><font face="arial, sans-serif" color="#000000">Research at TTIC Seminar Series</font></i></b></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif" color="#000000"> </font></p><p class="MsoNormal" style="font-family:Arial,Helvetica,sans-serif;margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" style="font-family:arial,sans-serif">TTIC is hosting a weekly seminar series presenting the research currently underway at the Institute. Every week a different TTIC faculty member will present their research.  The lectures are intended both for students seeking research topics and advisors and for the general TTIC and University of Chicago communities interested in hearing what their colleagues are up to.</font></p><font color="#888888" style="font-family:georgia,serif"><br></font></div><div><br></div>-- <br><div dir="ltr" data-smartmail="gmail_signature"><div dir="ltr"><b style="background-color:rgb(255,255,255)"><font color="#3d85c6">Brandie Jones </font></b><div><div><i><b style="background-color:rgb(255,255,255)"><font color="#3d85c6">Administrative Assistant</font></b></i></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Toyota Technological Institute</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">6045 S. Kenwood Avenue</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Chicago, IL  60637</font></span></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><a href="http://www.ttic.edu" target="_blank">www.ttic.edu</a> </font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><br></font></span></div><div><font color="#3d85c6"><div style="background-color:rgb(238,238,238)">Working Remote on Tuesdays</div></font></div></div></div></div>