December 16, 2016 - 4:00 pm
Max Tegmark, Josh Tenenbaum, Tomaso Poggio
December 16, 2016 - 3:00 pm
Kelsey Allen, Kevin Smith
People are incredibly proficient and flexibly tool users -- for instance, if we need to hammer a nail in but do not have access to a hammer, we can easily choose another object to strike the nail with while ignoring items that are inappropriate due to their size and/or material.
Kelsey and Kevin ...
Kelsey and Kevin ...
December 9, 2016 - 3:45 pm
"Research on artificial intelligence moves from 2-D to 3-D representations of the world—work that could lead to big advances in robotics and automated driving.
by Will Knight
There’s been some stunning progress in artificial intelligence of late, but it’s been surprisingly flat.
Now AI researchers are moving beyond two-dimensional images and pixels. Instead they’re building systems capable of picturing the three-dimensional world and taking...
December 9, 2016 - 10:45 am
“An exciting and important trend is the move in learning-based vision systems from just doing things with images to doing things with three-dimensional objects,” says Josh Tenenbaum, a professor in MIT’s Department of Brain and Cognitive Sciences. “That includes seeing objects in depth and modeling whole solid objects—not just recognizing that this pattern of pixels is a dog or a chair or table.”
(CBMM related work)
December 2, 2016 - 4:00 pm
Margaret Livingstone and Michael Arcaro (Harvard Medical School)
, Rebecca Saxe (MIT BCS)
December 1, 2016 - 2:15 pm
Larry Hardesty | MIT News Office
December 1, 2016
"MIT researchers and their colleagues have developed a new computational model of the human brain’s face-recognition mechanism that seems to capture aspects of human neurology that previous models have missed.
The researchers designed a machine-learning system that implemented their model, and they trained it to recognize particular faces by feeding it a battery of sample images. They found...
November 4, 2016 - 4:00 pm
Ilker Yildirim (CBMM, MIT), Goker Erdogan (U. Rochester); followed by a discussion with Josh Tenenbaum and...
Generative models and deep networks in brain/mind modeling (two 25 min talks + discussion/debate to follow).
November 4, 2016 - 3:00 pm
Jorg Scholvin (CBMM, Synthetic Neurobiology Group, MIT)
Topic: TBA
October 31, 2016 - 11:30 am
"Winrich Freiwald, associate professor and head of the Laboratory of Neural Systems, has received the 2016 W. Alden Spencer Award. The prize, given by Columbia University, recognizes outstanding research contributions in the field of neuroscience. Freiwald shares the award with his long-time collaborator Doris Y. Tsao of the California Institute of Technology. Freiwald and Tsao will receive the prize and present lectures on November 1 at the...
October 21, 2016 - 4:00 pm
Alan Yuille (CBMM, Johns Hopkins University)
Abstract: This talk describes work on detecting and parsing humans into joints and semantic parts. It combines deep networks with graphical models for reasoning about the spatial relations between joints. We discuss methods for dealing with occlusion and scale variations. Finally we describe...
October 12, 2016 - 4:00 pm
CBMM is thrilled to be chosen as one of NVIDIA’s Pioneers of AI Research - NVIDIA Early Access selections. The Center has received one of the first deliveries of the groundbreaking new DGX-1 rack-mounted deep learning supercomputers that NVIDIA CEO Jen-Hsun Huang unveiled at the GPU Technology Conference 2016. To start, this unit will be shared with two other groups at MIT - Computer Science and Artificial Intelligence Laboratory (CSAIL) and the...
October 7, 2016 - 4:00 pm
Pedro Tsividis and Josh Tenenbaum
NOTE - *Please bring a laptop, as this will be a participatory session. We will actually be playing video games for much of it. We encourage everyone to bring their laptop and actively participate.*
October 7, 2016 - 3:00 pm
Topic: Public outreach and science communication events and partnerships.
Agenda: Part of CBMM's education and knowledge transfer components are public outreach or science communication. Ellen Hildreth, CBMM coordinator for Education, will join us to discuss th If there is time, we will also go...
Agenda: Part of CBMM's education and knowledge transfer components are public outreach or science communication. Ellen Hildreth, CBMM coordinator for Education, will join us to discuss th If there is time, we will also go...
October 4, 2016 - 12:45 am
NIH anounced today that Prof. Nancy Kanwisher has received the 2016 NIH Director's Pioneer Award.
The NIH Director's Pioneer Award is on of the four awards in the NIH Common Fund's High-Risk, High-Reward Research program. The Pioneer Award supports individual scientists of "exceptional creativity, who propose pioneering and transforming approaches to major challenges in biomedical and behavioral research."