[Colloquium] REMINDER: 3/31 TTIC Colloquium: Dhruv Batra, Virginia Tech

[Mary Marre]

*When: *    Thursday, March 31st at 11:00 a.m.

*Where:*    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

*Speaker:*  Dhruv Batra, Virginia Tech


*Title:*
Towards Transparent Intelligent Systems: Diverse Predictions from
Perception Modules

*Abstract: *
What does a young child or a high-school student with no knowledge of
probability do when faced with a problem whose answer they are uncertain
of? They make guesses. Modern machine perception algorithms (for object
detection, pose estimation, or image captioning), despite dealing with
tremendous amounts of ambiguity, typically do not.

I will describe a line of work in my lab where we have been developing
machine perception and intelligent systems that convey their beliefs about
the world by producing a small set of diverse plausible hypotheses or
guesses about the state of the world (e.g. multiple segmentations for
objects in an image or human body keypoint locations or captions of an
image). I will discuss inference in structured and neural models,
connections to submodular maximization over a "doubly-exponential” space,
and show results on problems such as semantic segmentation, pose
estimation, and prepositional phrase attachment resolution in image
captions.

We view this line of work as a step towards making modern intelligent
systems transparent, by answering the question —  “What does this model
believe?”. I will also discuss further steps in this direction such as
answering the more difficult question — “Why does this model believe what
it does?” — on applications such as Visual Question Answering (VQA) and
Sequential VQA (or a visual Turing test).

*Bio: *
Dhruv Batra is an Assistant Professor at the Bradley Department of
Electrical and Computer Engineering at Virginia Tech (VT), where he leads
the VT Machine Learning & Perception group. He is a member of the Virginia
Center for Autonomous Systems (VaCAS) and the VT Discovery Analytics Center
(DAC).

Prior to joining VT, he was a Research Assistant Professor at Toyota
Technological Institute at Chicago (TTIC), a philanthropically endowed
academic computer science institute located on the University of Chicago
campus. He received his M.S. and Ph.D. degrees from Carnegie Mellon
University in 2007 and 2010 respectively, advised by Prof. Tsuhan Chen. In
past, he has held visiting positions at the Machine Learning Department at
CMU, CSAIL MIT, Microsoft Research, and Cornell University.

His research interests lie at the intersection of machine learning,
computer vision, and AI, with a focus on developing intelligent systems
that are able to concisely summarize their beliefs about the world,
integrate information and beliefs across different sub-components or
`modules' of AI (vision, language, reasoning) to extract a holistic view of
the world, and explain why they believe what they believe. In past, he has
also worked on topics such as interactive co-segmentation of large image
collections, human body pose estimation, action recognition, depth
estimation, and distributed optimization for inference and learning in
probabilistic graphical models.

He is a recipient of Carnegie Mellon Dean's Fellowship (2007), two Google
Faculty Research Awards (2013, 2015), Army Research Office (ARO) Young
Investigator Program (YIP) award (2014), the National Science Foundation
(NSF) CAREER award (2014), and Virginia Tech CoE Outstanding New Assistant
Professor award (2015). Research from his lab has been featured in
Bloomberg Business, The Boston Globe, MIT Technology Review, Newsweek, and
a number of popular press magazines and newspapers. His research is
supported by NSF, ARO, ARL, ONR, DARPA, Amazon, Google, Microsoft, and
NVIDIA.


Webpage: http://computing.ece.vt.edu/~dbatra



Host: Greg Shakhnarovich, greg at ttic.edu


For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20160330/41e10344/attachment.htm