[Theory] [TTIC Talks] 10/14 Research at TTIC: Baba C. Vemuri, University of Florida

[Brandie Jones]

*When:*         Friday, October 14th at *12:30pm CT*


*Where:*       Talk will be given *live, in-person* at

                       TTIC, 6045 S. Kenwood Avenue

                       5th Floor, Room 530



*Virtually:*    via Panopto (Livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=53793a5e-66c2-45cc-ac11-af2700e1817e>
)


*Who:*            Baba C. Vemuri, University of Florida



*Title:*            ManifoldNet: A Deep Neural Network for Manifold-valued
Data with Applications


*Abstract:    *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.




*Bio:     *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.

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.

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).


***********************************************************************************************

*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 ttic.edu/visitors
<http://ttic.edu/visitors>.*

***********************************************************************************************

*Research at TTIC Seminar Series*



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.


-- 
*Brandie Jones *
*Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu

Working Remote on Tuesdays
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20221007/501e3dcc/attachment-0001.html>