[BIC-announce] FW: CAMBAM Seminiar - Untangling object recognition: The convergence of systems neuroscience and computer vision

[Jennifer Chew, Ms.]

PLEASE DISCARD IF THIS IS A DUPLICATE.  THANK YOU. JENNIFER 
 

Jennifer Chew

McConnell Brain Imaging Centre

MNI - WB317

3801 University Street

Montreal, Qc  H3A 2B4

Telephone:  514-398-8554

Fax:  514-398-2975

 

 

________________________________

From: MNISTAFF - Montreal Neurological Institute Staff [mailto:MNISTAFF at LISTS.MCGILL.CA] On Behalf Of Enza Ferracane, Ms.
Sent: Thursday, September 30, 2010 3:37 PM
To: MNISTAFF at LISTS.MCGILL.CA
Subject: CAMBAM Seminiar



Date and Time: October 18th

Time: 4:15 - 5:30 pm

Place: Room 1101, McIntyre Building

Speaker: Jim DiCarlo

Associate Professor of Neuroscience

McGovern Institute for Brain Research and

Dept. of Brain and Cognitive Sciences

Massachusetts Institute of Technology

 

Topic: Untangling object recognition:   The convergence of systems neuroscience and computer vision.

 

Visual object recognition is a fundamental building block of memory and cognition, and is a central unsolved problem in both systems neuroscience and computer vision. In this talk, I will outline our ongoing efforts to synergize elements of these two research fields to attack the central challenge of object recognition. The computational crux of object recognition problem is that the recognition system (biological or artificial) must somehow tolerate tremendous image variation produced by different views of each object (the "invariance" problem). I will outline a framework and supporting empirical neuronal data that provide intuition on how this problem is solved (a stepwise "untangling" of object identity manifolds). But that intuition is not enough -- the space of hypothetical models is impossibly large, so that finding the visual system's solution without further constraints is like finding a needle in a haystack. 

 

In the first part of my talk, I will highlight ways in which systems neuroscience data are reducing the size of the hypothesis space, including the recent discovery that the primate visual system uses naturally occurring temporal contiguity cues in the visual environment to "learn" how to untangle object identity manifolds. In the second part of my talk, I will outline how new advances in computer vision and computing technology are beginning to appropriately navigate this neuroscience-reduced hypothesis space. I will conclude with a discussion of the definition of "success" in solving "real-world" object recognition, the rate of progress thus far, and speculation on what the future holds. 

 

 

 

Naomi M. Takeda

Administrative Coordinator for:

Drs. Barbara E. Jones, David S. Ragsdale,

        Christopher C. Pack and T. Stroh

Montreal Neurological Institute

McGill University

3801 University Street, #896

Montreal, Quebec, Canada

H3A 2B4

(  514-398-1913 (Direct Line)

Ê  514-398-5871

: naomi.takeda at mcgill.ca <mailto:naomi.takeda at mcgill.ca> 

P Please consider the environment before printing this email. Thank you!

 

P Devez-vous vraiment imprimer ce courriel? Pensons à l'environnement! Merci!