The Center for Brains, Minds & Machines

Netflix series features CBMM Researchers

Looking for something good to watch tonight? Netflix has released "Babies: Part 2" which includes CBMM PIs Rebecca Saxe, MIT (P2:E1 What Babies Know) and Laura Schulz, MIT (P2:E6 Toddlers).
The generalization problem of DNNs recognizing whether a pixel is inside or outside a closed curve.

In CBMM Memo 105, CBMM researchers solve the generalization issues by teaching the network using simple curves before seeing the most complex ones, which facilitates learning the “coloring routine”.
Rebecca Saxe adds Guggenheim Fellowship to her already remarkable CV

Congratulations to CBMM's Rebecca Saxe on her Guggenheim Fellowship, which will allow her to pursue her work “under the freest possible conditions.”
Can we Contain Covid-19 without Locking-down the Economy?

In this online webinar, Profs. Amnon Shashua and Shai Shalev-Shwartz will discuss their memorandum recently released covering their analysis of a risk-based selective quarantine model on Tuesday, March 31, 2020 @ 1:00pm ET. Registration required.
Brains, Minds + Machines Summer Course 2020 | MBL Woods Hole, MA

An intensive three-week course which will give a “deep end” introduction to the problem of intelligence. Course will be held from Aug. 6, 2020 through Aug. 27, 2020, at MBL, Woods Hole, MA, Application Deadline: April 27, 2020
2020 Dan David Prize winners

Demis Hassabis and Amnon Shashua, CBMM External Advisory Committee members, are the 2020 Dan David Prize winners for artificial intelligence. They share $1M for work on learning from experience in gaming and intelligent real-time vision, respectively.

past banners »

Videos | Support Us

The Center for Brains, Minds and Machines (CBMM)
is a multi-institutional NSF Science and Technology Center
dedicated to the study of intelligence - how the brain produces intelligent
behavior and how we may be able to replicate intelligence in machines.

The Center for Brains, Minds and Machines (CBMM) is a multi-institutional NSF Science and Technology Center dedicated to the study of intelligence - how the brain produces intelligent behavior and how we may be able to replicate intelligence in machines.

Summer course students working / Marine Biology Lab, Woodshole, MA

Brains, Minds, and Machines Summer Course

A CBMM flagship program, the Brains, Minds, and Machines Summer Course is an immersive 3-week course that provides a broad introduction to research on human & machine intelligence, combining three core disciplines — computation, neuroscience, and cognition — where students learn about common empirical & theoretical methods used in the field, and compelling results of this research, with an emphasis on the scientific mission of the Center.read more »

Prof. Nancy Kanwisher lecturing to a room full of students

The Science of Intelligence Learning Hub

Explore the science of intelligence through lectures, tutorials, and courses offered by the CBMM community, and experiment with modeling and data analysis tools used in neuroscience, cognitive science, and AI, to study intelligence in brains and machines!read more »

Featured news

Identifying a melody by studying a musician’s body language [MIT News]

June 25, 2020

The following story contains direct information on research efforts by CBMM PIs Antonio Torralba and Joshua Tenenbaum released in a jointly authored paper - https://arxiv.org/abs/2004.09476...

see more news »

Seminars + events

Please check back soon for upcoming CBMM Events.

see more events »

CBMM spotlight

Apurva Ratan Murty: High-Level Vision

Apurva Ratan Murty: High-Level Vision

Associated Research Thrust(s):

Neural Circuits for Intelligence

see more spotlights »

Highlighted publications

CBMM Memo No:

107

T. A. Poggio and Cooper, Y., “Theory II, Season 2: for overparametrized deep networks, SGD does not get stuck in local minima”. 2020.

CBMM Memo No:

110

M. Vuyyuru Reddy, Banburski, A., Pant, N., and Poggio, T., “Biologically Inspired Mechanisms for Adversarial Robustness”. 2020.

CBMM Memo No:

108

A. Rangamani, Rosasco, L., and Poggio, T., “For interpolating kernel machines, the minimum norm ERM solution is the most stable”. 2020.

see more Publications »

Featured video

Embedded thumbnail for Improving Generalization by Self-Training &amp; Self Distillation

Improving Generalization by Self-Training & Self Distillation

In supervised learning we often seek a model which minimizes (to epsilon optimality) a loss function over a training set, possibly subject to some (implicit or explicit) regularization. Suppose you...

see more videos »

Facebook Feed