![Embedded thumbnail for Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations [video]](https://cbmm.mit.edu/sites/default/files/styles/youtube_thumbnail_220w/public/youtube/6KBkS5qeCIE.jpg?itok=8kZHPDqw)
Recorded:
Dec 3, 2020
Uploaded:
December 3, 2020
Part of
All Captioned Videos, Publication Releases
CBMM Speaker(s):
Tiago Marques, James DiCarlo
Speaker(s):
Joel Dapello
Hear from the lead authors Tiago Maques (MIT), Joel Dapello (Harvard), and PI James DiCarlo (MIT), about their development of VOneNets, a new class of hybrid CNN vision models. This paper was accepted in the Advances in Neural Information Processing...
Recorded:
Nov 24, 2020
Uploaded:
November 25, 2020
Part of
All Captioned Videos, CBMM Research
Speaker(s):
Aleksander Madry, MIT
Abstract: Large-scale vision benchmarks have driven---and often even defined---progress in machine learning. However, these benchmarks are merely proxies for the real-world tasks we actually care about. How well do our benchmarks capture such tasks...
![Embedded thumbnail for Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning [video]](https://cbmm.mit.edu/sites/default/files/styles/youtube_thumbnail_220w/public/youtube/T0Ejs0dJFNc.jpg?itok=Fk7DDmNO)
Recorded:
Nov 23, 2020
Uploaded:
November 23, 2020
Part of
All Captioned Videos, Publication Releases, CBMM Research
CBMM Speaker(s):
Kevin Smith, Kelsey Allen, Joshua Tenenbaum
Authors Kelsey Allen, Kevin Smith, and Joshua Tenenbaum describe their newly published paper in PNAS about a new cognitive model that learns to use tools like humans do.
Recorded:
Nov 19, 2020
Uploaded:
November 23, 2020
Part of
All Captioned Videos, Computational Tutorials
Speaker(s):
Eli Pollock
Recurrent neural networks (RNNs) are a powerful model for neural and cognitive phenomena. However, interpreting these models can be a challenge. In this tutorial, we will discuss how dynamical systems theory provides some tools for understanding...
Recorded:
Nov 6, 2020
Uploaded:
November 6, 2020
Part of
All Captioned Videos, CBMM Research
ChildrenHelpingScience.com is a website where you and your family can find and participate in online research studies from universities around the world! You can search for the perfect study for your family. We have studies for all ages, starting...
Recorded:
Nov 3, 2020
Uploaded:
November 4, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Nicholas Roy
In the last few years, the ability for robots to understand and operate in the world around them has advanced considerably. Examples include the growing number of self-driving car systems, the considerable work in robot mapping, and the growing...
Recorded:
Oct 27, 2020
Uploaded:
November 4, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Kenneth Blum, Tomaso Poggio, Max Tegmark, Lorenzo Rosasco, Andrea Tacchetti
Speaker(s):
Daniela L Rus
Deep Learning has enjoyed an impressive growth over the past few years in fields ranging from visual recognition to natural language processing. Improvements in these areas have been fundamental to the development of self-driving cars, machine...
Recorded:
Oct 20, 2020
Uploaded:
November 2, 2020
Part of
All Captioned Videos, CBMM Research
CBMM Speaker(s):
Josh McDermott
Humans derive an enormous amount of information about the world from sound. This talk will describe our recent efforts to leverage contemporary neural networks to build models of these abilities and their instantiation in the brain. Such models have...
Recorded:
Oct 21, 2020
Uploaded:
October 21, 2020
Part of
Brains, Minds and Machines Summer Course 2020
CBMM Speaker(s):
Shimon Ullman
Recorded:
Aug 14, 2020
Uploaded:
October 21, 2020
Part of
All Captioned Videos, Brains, Minds and Machines Summer Course 2020
CBMM Speaker(s):
Nancy Kanwisher