Embedded thumbnail for Stability of overparametrized learning models
Recorded:
Apr 15, 2020
Uploaded:
April 15, 2020
Part of
All Captioned Videos, CBMM Research
CBMM Speaker(s):
Tomaso Poggio, Lorenzo Rosasco
Speaker(s):
Mikhail Belkin, Constantinos Daskalakis, Gil Strang
A panel discussion featuring Tomaso Poggio (CBMM), Mikhail Belkin (Ohio State University), Constantinos Daskalakis (CSAIL), Gil Strang (Mathematics) and Lorenzo Rosasco (University of Genova). Abstract: Developing theoretical foundations for...
Embedded thumbnail for Predictive Maps in the Brain
Recorded:
Apr 7, 2020
Uploaded:
April 7, 2020
Part of
All Captioned Videos, CBMM Research
CBMM Speaker(s):
Samuel Gershman
Sam Gershman, Harvard University Abstract: In this talk, I will present a theory of reinforcement learning that falls in between "model-based" and "model-free" approaches. The key idea is to represent a "predictive map" of the environment, which can...
Embedded thumbnail for Can we Contain Covid-19 without Locking-down the Economy?
Recorded:
Apr 1, 2020
Uploaded:
April 1, 2020
Part of
All Captioned Videos, CBMM Special Seminars
CBMM Speaker(s):
Amnon Shashua
Speaker(s):
Shai Shalev-Shwartz
Abstract:
We present an analysis of a risk-based selective quarantine model where the population is divided into low and high-risk groups. The high-risk group is quarantined until the low-risk group achieves herd-immunity. We tackle the...
Embedded thumbnail for A conversation with Michael R. Douglas
Recorded:
Feb 25, 2020
Uploaded:
March 9, 2020
Part of
Scientific Interviews
CBMM Speaker(s):
Andrzej Banburski
Speaker(s):
Michael R. Douglas, Simons Center for Geometry and Physics at Stony Brook University
On February 25, 2020, CBMM Postdoctoral Fellow Andrzej Banburski took the opportunity to sit down and chat briefly with Michael R. Douglas of the Simons Center for Geometry and Physics at Stony Brook University.
Embedded thumbnail for Exploring how the nervous system produces movement sequences
Recorded:
Jul 9, 2019
Uploaded:
March 9, 2020
Part of
All Captioned Videos, CBMM Special Seminars
Speaker(s):
Andrew Seeds - Institute for Neurobiology, University of Puerto Rico, Medical Sciences Campus
Embedded thumbnail for How will we do mathematics in 2030?
Recorded:
Feb 25, 2020
Uploaded:
February 26, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Michael R. Douglas, Stony Brook University
Embedded thumbnail for Life as GIM in a GAN psychophysics of Cephalopod camouflage & perception: some conjectures
Recorded:
May 21, 2018
Uploaded:
February 26, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Jonathan Miller, OIST
Embedded thumbnail for Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs [video]
Recorded:
Oct 25, 2019
Uploaded:
February 10, 2020
Part of
All Captioned Videos, Publication Releases
CBMM Speaker(s):
Martin Schrimpf
Speaker(s):
Jonas Kubilius
Lead authors Jonas Kubilius and Martin Schrimpf discuss the challenges of measuring how closely neural networks match the brain and present a new scoring method Brain-Score they have developed to evaluate models of the brain’s ventral stream at...
Embedded thumbnail for Doing for robots what nature did for us
Recorded:
Feb 4, 2020
Uploaded:
February 5, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Leslie P. Kaelbling
Abstract: We, as robot engineers, have to think hard about our role in the design of robots and how it interacts with learning, both in "the factory" (that is, at engineering time) and in "the wild" (that is, when the robot is delivered to a...
Embedded thumbnail for Finding Friend and Foe in Multi-Agent Games [video]
Recorded:
Dec 16, 2019
Uploaded:
December 20, 2019
Part of
All Captioned Videos, Publication Releases
CBMM Speaker(s):
Max Kleiman-Weiner
Speaker(s):
Jack Serrino
Co-authors Max Kleiman-Weiner and Jack Serrino discuss their latest publication where they created a new algorithm. The algorithm that the team developed, dubbed DeepRole, has three components. First, it plays against itself, iteratively, with...

Pages