![Embedded thumbnail for The Indoor-Training Effect: Unexpected Gains from Distribution Shifts in the Transition Function [video]](https://cbmm-mit-edu.ezproxyberklee.flo.org/sites/default/files/styles/youtube_thumbnail_220w/public/youtube/JEyP1vLSmD8.jpg?itok=HQbzO4Sc)
Recorded:
Jan 29, 2025
Uploaded:
January 29, 2025
Part of
All Captioned Videos, Publication Releases
CBMM Speaker(s):
Spandan Madan
Speaker(s):
Serena Bono
Authors Serena Bono (MIT Media Lab) and Spandan Madan (Harvard University) describe their latest paper and findings on training reinforcement learning models and their testing abilities.
Recorded:
Jan 10, 2025
Uploaded:
January 10, 2025
Part of
All Captioned Videos
CBMM Speaker(s):
Samuel Gershman, Josh McDermott, Carlos Ponce, Maria Fernanda De La Torre, Leyla Isik, Boris Katz, James DiCarlo, Kohitij Kar, Gabriel Kreiman, Winrich Freiwald, Mengmi Zhang, Will Xiao, Morgan Talbot, Ed Boyden, Akshay Rangamani
Over the last 11+ years, the Center for Brains, Minds, and Machines has become a place of gathering brilliant minds to discuss and solve the challenges and questions of intelligence, organic and artificial. Hear from a few of our members, and others...
![Embedded thumbnail for Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex [video]](https://cbmm-mit-edu.ezproxyberklee.flo.org/sites/default/files/styles/youtube_thumbnail_220w/public/youtube/bhXB-djJ9lc.jpg?itok=d-DVejVs)
Recorded:
Dec 11, 2024
Uploaded:
December 11, 2024
Part of
All Captioned Videos, Publication Releases
CBMM Speaker(s):
Spandan Madan
Authors: Spandan Madan, Will Xiao, Mingran Cao, Hanspeter Pfister, Margaret Livingstone, Gabriel Kreiman
Link to Paper: https://arxiv.org/abs/2406.16935
Abstract: We characterized the generalization capabilities of DNN-based encoding models when...
Recorded:
Nov 12, 2024
Uploaded:
November 19, 2024
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Tomaso Poggio, Ila Fiete, Haim Sompolinsky
Speaker(s):
Philip Isola, MIT, Eran Malach, Harvard
In a society that is confronting the new age of AI in which LLMs begin to display aspects of human intelligence, understanding the fundamental theory of deep learning and applying it to real systems is a compelling and urgent need. This panel will...
Recorded:
Nov 13, 2024
Uploaded:
November 19, 2024
Part of
All Captioned Videos, Computational Tutorials
Speaker(s):
Rachel Denison, Boston University
Attention is a cognitive process that allows us to prioritize the sensory information that is most relevant for our behavioral goals. In a successful class of computational models of attention, attention biases neural responses through its...
Recorded:
Oct 9, 2024
Uploaded:
October 28, 2024
Part of
All Captioned Videos, Computational Tutorials
Speaker(s):
Djuna von Maydell, MIT
Understanding how training data influences model predictions ("data attribution") is an active area of machine learning research. In this tutorial, we will introduce a data attribution method (datamodels: https://gradientscience.org/datamodels-1/)...
Recorded:
Oct 1, 2024
Uploaded:
October 21, 2024
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Noah Goodman
Noah Goodman, Stanford University
Recorded:
Oct 10, 2024
Uploaded:
October 10, 2024
Part of
All Captioned Videos, Scientific Interviews
Recorded:
Sep 10, 2024
Uploaded:
September 26, 2024
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Michael Littman, Brown University
Abstract: It is immensely empowering to delegate information processing work to machines and have them carry out difficult tasks on our behalf. But programming computers is hard. The traditional approach to this problem is to try to fix people: They...
Recorded:
Aug 13, 2024
Uploaded:
September 23, 2024
Part of
All Captioned Videos, Brains, Minds and Machines Summer Course 2024
Speaker(s):
Vikash Mansinghka, MIT