[Colloquium] CANCELLED: CS Seminar March 17: Michael Everett, MIT

[Sandra Wallace]

All,

This seminar is cancelled.  Please remove from your calendar.

Thanks,

Sandra



> On Mar 8, 2021, at 2:30 PM, Sandra Wallace <swallace at cs.uchicago.edu> wrote:
> 
> UNIVERSITY OF CHICAGO
> DEPARTMENT OF COMPUTER SCIENCE
> SEMINAR:
> 
>  <PastedGraphic-4.tiff>
> 
> Michael Everett
> Massachusetts Institute of Technology (MIT)
> 
> Wednesday, March 17th at 3:00 pm
> 
> Join via zoom (enables questions):
> https://uchicago.zoom.us/j/99783583051?pwd=UWovNXZab2ZiZGdlSlY5aW0rcjZmZz09 <https://uchicago.zoom.us/j/99783583051?pwd=UWovNXZab2ZiZGdlSlY5aW0rcjZmZz09>
> Meeting ID:  997 8358 3051
> Passcode:  uccs2021
>  
> Or
> 
> Watch via live stream:
> http://live.cs.uchicago.edu/michaeleverett/ <http://live.cs.uchicago.edu/michaeleverett/>
> 
> Title:  Certifiable Learning Machines: Developing resilient autonomous systems for society
> 
> Abstract:  Autonomous robots have the potential to transform our everyday lives, yet most of today's autonomous robots struggle in the real world. This talk will first describe our work toward a new generation of robots that learn to handle the highly dynamic and uncertain nature of human environments. In particular, I will highlight the importance of obtaining accurate cost-to-go models, which we show can be learned from self-play or aerial imagery for a variety of applications, from navigation among pedestrians to last-mile delivery. The talk will then dive into the challenges of certifying the safety and robustness properties of machines that learn. I will describe our work that uses convex relaxations and set partitioning to simplify the analysis of highly nonlinear neural networks used across AI. These analysis tools led to the first framework for deep reinforcement learning that is certifiably robust to adversarial attacks and noisy sensor data. The tools also enable reachability analysis -- the calculation of all states that a system could reach in the future -- for systems that employ neural networks in the feedback loop, which provides another notion of safety for learning machines that interact with uncertain environments. Finally, I will discuss my long-term vision to spark a new era of autonomy defined by robots that are resilient, dependable, and ready to support humans throughout the real world.
> 
> Bio:  Michael Everett received the S.B., S.M., and Ph.D. degrees in mechanical engineering from the Massachusetts Institute of Technology (MIT), in 2015, 2017, and 2020, respectively. He is currently a Postdoctoral Associate with the Department of Aeronautics and Astronautics at MIT. His research lies at the intersection of machine learning, robotics, and control theory, with specific interests in the theory and application of certifiable learning machines. He was an author of works that won the Best Paper Award on Cognitive Robotics at IROS 2019, the Best Student Paper Award and a Finalist for the Best Paper Award on Cognitive Robotics at IROS 2017, and a Finalist for the Best Multi-Robot Systems Paper Award at ICRA 2017. He has been interviewed live on the air by BBC Radio and his team’s robots were featured by Today Show and the Boston Globe.
> 
> 
> Host:  Michael Maire
> _______________________________________________
> Colloquium mailing list  -  Colloquium at mailman.cs.uchicago.edu
> https://mailman.cs.uchicago.edu/mailman/listinfo/colloquium
> _______________________________________________
> faculty mailing list  -  faculty at mailman.cs.uchicago.edu
> https://mailman.cs.uchicago.edu/mailman/listinfo/faculty
> _______________________________________________
> Faculty-admins mailing list
> Faculty-admins at mailman.cs.uchicago.edu
> https://mailman.cs.uchicago.edu/cgi-bin/mailman/listinfo/faculty-admins

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20210315/3386ad3a/attachment.html>