CBMM Special Seminar: Development of Cortical Representations in Human and Macaque Infants

Dec 2, 2016 - 4:00 pm
Rebecca Saxe and Margaret Livingstone
Venue:  McGovern Institute for Brain Research, MIT Bldg. 46 Room 3002 (Singleton) Address:  43 Vassar St, Cambridge MA, 02139 Speaker/s:  Margaret Livingstone and Michael Arcaro (Harvard Medical School) Rebecca Saxe (MIT BCS) Organizer:  Elisa Pompeo Organizer Email:  epompeo@mit.edu

CBMM Workshop on "Speech Representation, Perception and Recognition"

Feb 2, 2017 - 8:00 am
Venue:  McGovern Institute for Brain Research

The two-day workshop on "Speech representation, perception and recognition" is organized by the NSF-funded, MIT-based, Center for Brains Minds and Machines (CBMM), on February 2-3, 2017 at the McGovern Institute for Brain Research, MIT, Cambridge, MA.

The workshop will feature invited talks from leading speech researchers as well as focused discussion sessions. It will bring together experts in the fields of neuroscience, perception, development, machine learning, automatic speech recognition and speech synthesis. The only goal for the workshop is talks and discussion. 

We aim to focus on the computations and learning involved in human speech understanding and that are required for speech-enabled machines, following the Center's mission to understand intelligence in brains and replicate it in machines. 

Registration is open through RSVP.   

Please visit the workshop mini-page for more information - https://cbmm.mit.edu/speech-workshop

Organizer:  Josh McDermott Georgios Evangelopoulos

CBMM Research Meeting: Parsing Humans with Comp

Oct 21, 2016 - 4:00 pm
Photo of Alan Yuille
Venue:  Northwest Science Building, Room 243, Harvard University Speaker/s:  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 compositional methods for extracting key-point motifs for classifying human actions.

Pages

Subscribe to Front page feed