Prof. Daniela Rus, Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) , Deputy Dean of Research for the Schwarzman College of Computing, MIT,
Research website: http://danielarus.csail.mit.edu/,
Dr. Ramin Hasani, CSAIL, MIT,
Research website: http://www.raminhasani.com/
The Fall 2021 Brains, Minds, and Machines (BMM) Seminar Series will be hosted in a hybrid format.
Please see the information included below regarding attending the event either in-person or remotely via Zoom connection
Abstract: In this talk, we will discuss the nuts and bolts of the novel continuous-time neural network models: Liquid Time-Constant (LTC) Networks. Instead of declaring a learning system's dynamics by implicit nonlinearities, LTCs construct networks of linear first-order dynamical systems modulated via nonlinear interlinked gates. LTCs represent dynamical systems with varying (i.e., liquid) time-constants, with outputs being computed by numerical differential equation solvers. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations, and give rise to improved performance on time-series prediction tasks compared to advance recurrent network models.
Dr. Daniela Rus is the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and Computer Science and Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. Rus’s research interests are in robotics, mobile computing, and data science. Rus is a Class of 2002 MacArthur Fellow, a fellow of ACM, AAAI and IEEE, and a member of the National Academy of Engineers, and the American Academy of Arts and Sciences. She earned her PhD in Computer Science from Cornell University. Prior to joining MIT, Rus was a professor in the Computer Science Department at Dartmouth College.
Dr. Ramin Hasani is a postdoctoral associate and a machine learning scientist at MIT CSAIL. His primary research focus is on the development of interpretable deep learning and decision-making algorithms for robots. Ramin received his Ph.D. with honors in Computer Science at TU Wien, Austria. His dissertation on liquid neural networks was co-advised by Prof. Radu Grosu (TU Wien) and Prof. Daniela Rus (MIT). Ramin is a frequent TEDx speaker. He has completed an M.Sc. in Electronic Engineering at Politecnico di Milano (2015), Italy, and has got his B.Sc. in Electrical Engineering – Electronics at Ferdowsi University of Mashhad, Iran (2012).
Guidance for attending in-person:
MIT attendees will need to be registered via the MIT COVIDpass system to have access to MIT Building 46.
Please visit URL https://covidpass.mit.edu/ for more information regarding MIT COVIDpass.
MIT is currently welcoming visitors to attend talks in person. All visitors to the MIT campus are required to follow MIT COVID19 protocols, see URL https://now.mit.edu/policies/campus-access-and-visitors/. Specifically, visitors are required to wear a face-covering/mask while indoors and use the new MIT TIM Ticket system for accessing MIT buildings. Per MIT’s event policy, use of the Tim Tickets system is required for all indoor events; for information about this and other current MIT policies, visit MIT Now.
Link to this event's MIT TIM TICKET: https://tim-tickets.atlas-apps.mit.edu/bhsy3hztLJvG2EMi7
To access MIT Bldg. 46 with a TIM Ticket, please enter the building via the McGovern/Main Street entrance - 524 Main Street (on GPS). This entrance is equipped with a QR reader that can read the TIM Ticket. A map of the location of, and an image of, this entrance is available at URL: https://mcgovern.mit.edu/contact-us/
General TIM Ticket information:
A visitor may use a Tim Ticket to access Bldg. 46 any time between 6 a.m. and 6 p.m., M-F
A Tim Ticket is a QR code that serves as a visitor pass. A Tim Ticket, named for MIT’s mascot, Tim the Beaver, is the equivalent of giving someone your key to unlock a building door, without actually giving up your keys.
This system allows MIT to collect basic information about visitors entering MIT buildings while providing MIT hosts a convenient way to invite visitors to safely access our campus.
Information collected by the TIM Ticket:
- Phone number
- Email address
- COVID-19 vaccination status (i.e., whether fully vaccinated or exempt)
- Symptom status and wellness information for the day of visit
Visitors must acknowledge and agree to terms for campus access, confirm basic contact information, and submit a brief attestation about health and vaccination status. Visitors should complete these steps at least 30 minutes before scanning into an MIT building.
For more information on the TIM Tickets, please visit https://covidapps.mit.edu/visitors#for-access
Details to attend talk remotely via Zoom:
MIT Building 46 | Brain and Cognitive Sciences Complex, 43 Vassar Street, Cambridge MA 02139