[Colloquium] [TTIC Talks] REMINDER: 3/5 Talks at TTIC: Xavier Boix, Massachusetts Institute of Technology

[Alicia McClarin]

*When:*      Thursday, March 5th at 11:00am



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



*Who: *       Xavier Boix, Massachusetts Institute of Technology

*Title*:         Using Neuro-inspired Tools to Understand Deep Neural
Networks

*Abstract*: Deep Neural Networks (DNNs) are driving a new industrial
revolution. Yet, we currently have no way to make rigorous claims about
DNNs' behavior as we are largely ignorant of their learned mechanisms, ie.
the "black-box problem". Understanding these mechanisms is necessary to
develop AI applications that are explainable, reliable and verifiable. A
promising strand of research that I have been pursuing to understand
DNNs has been borrowing insights and tools from neuroscience, ie.
articulating hypothesis and testing them as if DNNs were another brain. My
talk will review recent progress made using such neuro-inspired approach to
understand the failures and the successes of DNNs. Namely, I will speak
about our efforts in detecting severe failures modes of DNNs for object
recognition in the real world, and on the progress to understand how the
DNNs’ accuracy is maintained when the network's width is increased.
Finally, I will argue that not only does the neuro-inspired approach expand
our understanding of DNNs, but it also provides a roadmap for improving
their limitations in the future.

Bio:          Xavier Boix is a postdoctoral researcher at the Department of
Brain and Cognitive Sciences at MIT (since 2014) and a research affiliated
at Harvard (since 2017). He is also a member of multidisciplinary NSF
research center for Brains, Minds and Machines (CBMM). Xavier obtained a
doctorate from ETH Zurich (2014) and completed a postdoc at the National
University of Singapore (2016). He also won the PASCAL VOC Challenge in
Semantic Segmentation in 2010. His current research lives at the
intersection of engineering of deep neural networks, theoretical machine
learning and neuroscience. His goal is to develop empirically-grounded
theories that explain deep neural networks and to build applications that
can have a positive impact.

*Host:       *Greg Shakhnarovich <greg at ttic.edu>

-- 
*Alicia McClarin*
*Toyota Technological Institute at Chicago*
*6045 S. Kenwood Ave., **Office 504*
*Chicago, IL 60637*
*773-834-3321*
*www.ttic.edu* <http://www.ttic.edu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20200304/af1d9a29/attachment.html>