Embedded thumbnail for Next-generation recurrent network models for cognitive neuroscience
Recorded:
Jun 15, 2021
Uploaded:
June 16, 2021
Part of
CBMM Special Seminars
CBMM Speaker(s):
Guangyu Robert Yang
Recurrent Neural Networks (RNNs) trained with machine learning techniques on cognitive tasks have become a widely accepted tool for neuroscientists. In comparison to traditional computational models in neuroscience, RNNs can offer substantial...
Embedded thumbnail for Banach Space Representer Theorems for Neural Networks
Recorded:
Jun 8, 2021
Uploaded:
June 9, 2021
Part of
CBMM Special Seminars
Speaker(s):
Robert Nowak
Prof. Robert D. Nowak, University of Wisconsin-Madison Abstract: This talk presents a variational framework to understand the properties of functions learned by neural networks fit to data. The framework is based on total variation semi-norms...
Embedded thumbnail for Something Else About Working Memory
Recorded:
May 11, 2021
Uploaded:
May 12, 2021
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Earl K. Miller
Prof. Earl K. Miller, Picower Institute for Learning and Memory, BCS Dept., MIT Abstract: Working memory is the sketchpad of consciousness, the fundamental mechanism the brain uses to gain volitional control over its thoughts and actions. For the...
Embedded thumbnail for Compositional Generative Networks & Adversarial Examiners: Beyond the Limitations of Current AI
Recorded:
May 4, 2021
Uploaded:
May 5, 2021
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
CBMM Speaker(s):
Alan L. Yuille
Current AI visual algorithms are very limited compared to the robustness and flexibility of the human visual system. These limitations, however, are often obscured by the standard performance measures (SPMs) used to evaluate vision algorithms which...
Embedded thumbnail for CBMM Panel Discussion: “Testing generative models in the brain”
Recorded:
Apr 13, 2021
Uploaded:
April 16, 2021
Part of
All Captioned Videos, CBMM Special Seminars
CBMM Speaker(s):
Joshua Tenenbaum, Samuel Gershman
Speaker(s):
Talia Konkle, Ila Fiete
Panelists: Profs. Talia Konkle (Harvard), Josh Tenenbaum (MIT), and Sam Gershman (Harvard)
Moderator: Prof. Ila Fiete (MIT
Embedded thumbnail for Exiting flatland: measuring, modeling, and synthesizing animal behavior in 3D
Recorded:
Apr 8, 2021
Uploaded:
April 9, 2021
Part of
All Captioned Videos, Computational Tutorials
Speaker(s):
Jesse Marshall, Harvard University
Mechanistic studies of complex, ethological animal behaviors are poised to define the next decade of neuroscience. Fully understanding the ontogeny, evolution, and neural basis of these behaviors requires precise 3D measurements of their underlying...
Embedded thumbnail for Invariant representation of physical stability in the human brain
Recorded:
Mar 16, 2021
Uploaded:
March 23, 2021
Part of
All Captioned Videos, CBMM Research
CBMM Speaker(s):
R.T. Pramod
Successful engagement with the world requires the ability to predict what will happen next. Although some of our predictions are related to social situations concerning other people and what they will think and do, many of our predictions concern...
Embedded thumbnail for From Associative Memories to Deep Networks and from Associative Memories to Universal Machines
Recorded:
Mar 10, 2021
Uploaded:
March 9, 2021
Part of
All Captioned Videos, CBMM Special Seminars
CBMM Speaker(s):
Tomaso Poggio, Kenneth Blum
Speaker(s):
Christos Papadimitriou, Santosh Vempala
Panelists: Profs. Christos Papadimitriou (Columbia), Tomaso A. Poggio (CBMM, MIT) and Santosh Vempala (Georgia Tech)
Moderator: Kenneth Blum Abstract: About fifty years ago, holography was proposed as a model of associative memory. Associative...
Embedded thumbnail for Common Sense Physics and Structured Representation in the Era of Deep Learning
Recorded:
Mar 2, 2021
Uploaded:
March 3, 2021
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Prof. Murray Shanahan, Imperial College London / Google DeepMind
The challenge of endowing computers with common sense remains one of the major obstacles to achieving the sort of general artificial intelligence envisioned by the field’s founders. A large part of human common sense pertains to the physics of the...
Embedded thumbnail for Computation and Learning with Assemblies of Neurons
Recorded:
Feb 23, 2021
Uploaded:
February 24, 2021
Part of
All Captioned Videos, Brains, Minds and Machines Seminar Series
Speaker(s):
Santosh Vempala, Georgia Tech
Prof. Santosh Vempala, Georgia Tech Abstract: Despite great advances in ML, and in our understanding of the brain at the level of neurons, synapses, and neural circuits, we still have no satisfactory explanation for the brain's performance in...

Pages