Photo of Prof. Robert D. Nowak
June 8, 2021 - 2:00 pm
This seminar talk will be hosted remotely via Zoom.
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 defined in the Radon domain, which is naturally suited to the analysis of neural activation functions (ridge...
Photo of Prof. Earl Miller (PILM, MIT)
May 11, 2021 - 4:00 pm
Prof. Earl K. Miller, Picower Institute for Learning and Memory, BCS Dept., MIT
Host: Prof. Matt Wilson (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 past 50 years, working memory has been thought to rely on cortical neurons that fire continuous...
Photo of Prof. Alan L. Yuille
May 4, 2021 - 2:30 pm
Hosted via Zoom
Prof. Alan L. Yuille (JHU)
Abstract: 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 favor data-driven methods. SPMs, however...
Photo of Prof. Aude Oliva
March 30, 2021 - 4:00 pm
Hosted via Zoom
Prof. Aude Oliva, Senior Research Scientist, CSAIL; MIT Director MIT-IBM Watson AI Lab; Director MIT Quest...
Dear Friends,
Unfortunately, Prof. Aude Oliva is feeling unwell and we have canceled today’s talk “Mapping Responses in the Human Brain Through Space and Time.” We will reschedule this talk in the near future.
Host: Prof. Leyla Isik (JHU)
Abstract: The human brain is a time machine; We are...
Portrait of Prof. Murray Shanahan
March 2, 2021 - 2:00 pm
Prof. Murray Shanahan, Imperial College London
Host: Prof. Josh Tenenbaum (MIT)
Abstract:  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...
Photo of Prof. Santosh Vempala
February 23, 2021 - 4:00 pm
Prof. Santosh Vempala, Georgia Tech.
Host: Prof. Tomaso Poggio (MIT)
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 perception, cognition, language, memory, behavior; as Nobel...
Photo: David Sella
November 3, 2020 - 4:00 pm
Nick Roy, CSAIL, AeroAstro, MIT
Abstract: 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 interest in home and service robots. However...
October 27, 2020 - 4:00 pm
Panelists: Tomaso A Poggio (CBMM), Daniela L Rus (CSAIL), Max Tegmark (Physics), Lorenzo Rosasco (IIT), and...
Abstract: 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 translation  and healthcare applications....
September 29, 2020 - 4:00 pm
Profs. Jim DiCarlo, Tomaso A Poggio, and Joshua Tenenbaum
Panel details:
Profs. Jim DiCarlo, Tomaso A Poggio, and Joshua Tenenbaum will discuss and debate the relationship between engineering and science in CBMM and the field:
We all believe that if we want to understand how our brain computes intelligence, we need a synergistic combination of the science...
September 15, 2020 - 4:00 pm
Hosted via Zoom
Prof. George Em Karniadakis, Brown University
Abstract: It is widely known that neural networks (NNs) are universal approximators of continuous functions, however, a less known but powerful result is that a NN with a single hidden layer can approximate accurately any nonlinear continuous operator. This universal approximation theorem of...
June 23, 2020 - 2:00 pm
Marco Baroni, Facebook AI Research (Paris) and Catalan Institute for Research and Advanced Studies (Barcelona...
Is compositionality over-rated? A view from emergent neural network language analysis
Compositionality is the property whereby linguistic expressions that denote new composite meanings are derived by a rule-based combination of expressions denoting their parts. Linguists agree that...
April 21, 2020 - 4:00 pm
Luca Carlone
Spatial perception has witnessed an unprecedented progress in the last decade. Robots are now able to detect objects and create large-scale maps of an unknown environment, which are crucial capabilities for navigation and manipulation. Despite these advances, both researchers and...
March 31, 2020 - 1:00 pm
Zoom Webinar - registration Required
Profs. Amnon Shashua and Shai Shalev-Shwartz, The Hebrew University of Jerusalem, Israel
Registration is required, please see details below.
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 question...
Photo of Lior Wolf
March 16, 2020 - 4:00 pm
Singleton Auditorium
Lior Wolf, Tel Aviv University and Facebook AI Research.
Please note that this talk has been canceled.
We will reschedule his talk at the earliest convenience.
Abstract: Hypernetworks, also known as dynamic networks, are neural networks in which the weights of at least some of the layers vary dynamically based on the input. Such networks have...
Michael Douglas
February 25, 2020 - 4:00 pm
Singleton Auditorium
Michael Douglas, Stony Brook
Title:  How will we do mathematics in 2030 ?
We make the case that over the coming decade, computer assisted reasoning will become far more widely used in the mathematical sciences. This includes interactive and automatic theorem verification, symbolic algebra,  and emerging technologies...