April 18, 2020 - 9:45 am
Are we really going to bet that we can go back to life as normal without proper coronavirus tracking in place? By Thomas L. Friedman “LIBERATE MINNESOTA!” “LIBERATE MICHIGAN!” “LIBERATE VIRGINIA.” With these three short tweets last week, President Trump attempted to kick off the post-lockdown phase of America’s coronavirus crisis. It should be called: “American Russian roulette: The Covid-19 version.’’ What Trump was saying with those tweets was...
April 16, 2020 - 11:00 am
Altruism toward strangers grows out of the emotional attachment between babies and their caregivers. By Alison Gopnik The last few weeks have seen extraordinary displays of altruism. Ordinary people have transformed their lives—partly to protect themselves and the people they love from the Covid-19 pandemic, but also to help other people they don’t even know. But where does altruism come from? How could evolution by natural selection produce...
April 14, 2020 - 2:00 pm
Tomaso Poggio (CBMM), Mikhail Belkin (Ohio State University), Constantinos Daskalakis (CSAIL), Gil Strang (...
Developing theoretical foundations for learning is a key step towards understanding intelligence. Supervised learning is a paradigm in which natural or artificial networks learn a functional relationship from a set of n input-output training examples. A main challenge for the theory is...
April 14, 2020 - 10:00 am
MIT professors Sabine Iatridou, Jonathan Gruber, and Rebecca Saxe have been selected to pursue their work “under the freest possible conditions.” Julie Pryor | McGovern Institute for Brain Research MIT faculty members Sabine Iatridou, Jonathan Gruber, and Rebecca Saxe are among 175 scientists, artists, and scholars awarded 2020 fellowships from the John Simon Guggenheim Foundation. Appointed on the basis of prior achievement and exceptional...
April 7, 2020 - 2:00 pm
Sam Gershman, Harvard/CBMM
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 then be used to efficiently compute values. I show how such a map explains many...
lonley man wlaking on a beach
April 2, 2020 - 10:00 am
A study on isolation’s neural underpinnings implies many may feel literally “starved” for contact amid the COVID-19 pandemic By Lydia Denworth Loneliness hurts. It is psychologically distressing and so physically unhealthy that being lonely increases the likelihood of an earlier death by 26 percent. But the feeling may serve a purpose. Psychologists theorize it hurts so much because, like hunger and thirst, loneliness acts as a biological alarm...
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...
March 10, 2020 - 4:00 pm
MIT 46-5165
There will be no meeting on Tues., March 10, 2020
March 10, 2020 - 2:15 pm
In years to come, robots could assist human users in a variety of ways, both when they are inside their homes and in other settings. To be more intuitive, robots should be able to follow natural language commands and instructions, as this allows users to communicate with them just as they would with other humans. With this in mind, researchers at MIT's Center for Brains, Minds & Machines have recently developed a sampling-based robotic...
confused red robot
March 9, 2020 - 11:15 am
Deep-learning models can spot patterns that humans can't. But software still can't explain, say, what caused one object to collide with another. by Will Knight Here’s a troubling fact. A self-driving car hurtling along the highway and weaving through traffic has less understanding of what might cause an accident than a child who’s just learning to walk. A new experiment shows how difficult it is for even the best artificial intelligence systems...
March 4, 2020 - 10:00 am
Computer model of face processing could reveal how the brain produces richly detailed visual representations so quickly. Anne Trafton | MIT News Office When we open our eyes, we immediately see our surroundings in great detail. How the brain is able to form these richly detailed representations of the world so quickly is one of the biggest unsolved puzzles in the study of vision. Scientists who study the brain have tried to replicate this...
February 28, 2020 - 2:00 pm
Researchers discover that no magic is required to explain why deep networks generalize despite going against statistical intuition. by Kris Brewer Introductory statistics courses teach us that, when fitting a model to some data, we should have more data than free parameters to avoid the danger of overfitting — fitting noisy data too closely, and thereby failing to fit new data. It is surprising, then, that in modern deep learning the practice...
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...
February 24, 2020 - 1:30 pm
BEHIND THE PAPER Moving away from alchemy into the age of science for deep learning by Andrzej Banburski Imagine you’re back in elementary school and just took your first statistics course on fitting models to data. One thing you’re sure about is that a good model surely should have less parameters than data (think of fitting ten data points with a line, i.e. two parameters), otherwise you’ll ruin the predictivity of your model by overfitting....