[Colloquium] REMINDER: 8/29 TTIC Colloquium: Gal Chechik, Bar-Ilan University/Google (NOTE - UNUSUAL DAY)

Mary Marre via Colloquium colloquium at mailman.cs.uchicago.edu
Tue Aug 28 12:33:47 CDT 2018


*When:      Wednesday, August 29th at 11:00 am  **NOTE - Unusual Day** *



*Where:     *TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who:        *Gal Chechick; Bar-Ilan University/Google



*Title:*        Talking about images

*Abstract:*
Learning to understand and describe complex visual scenes raises hard
challenges: it often requires to learn to generalize effectively from few
samples and sometimes take into account the unseen context of an image. I
will discuss two research thrusts for facing these challenges. First,
modelling context, I will discuss an unsupervised approach to model
listener expectations during communication, and an approach to describe
images in a natural but discriminative language. Second, I will discuss
leveraging small label sets for large-scale image understanding.

Joint work with Rama Vednatam, Lior Bracha, Yuval Atzmon, Tom Duerig, Ariel
Fuxman, Neil alldrin, Devi Parikh, Kevin Murphy and Samy Bengio.


*Bio:*
Gal Chechik is a staff research scientist at Google Brain, California and
an Associate  Professor at the Gonda Brain research institute in Bar-Ilan
U. Israel. His research spans learning in brains and machines, including
large-scale learning algorithms for machine perception, and analysis of
representation and development of mammalian brains.  Gal earned his PhD
from the Hebrew University in Jerusalem, followed by a postdoctoral
research at Stanford. He is the author ~75 papers and ~35 patents,
including publications in Nature Biotech, Cell, and PNAS.


Host:  Greg Shakhnarovich <greg at ttic.edu>



For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 523*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Wed, Aug 22, 2018 at 4:49 PM, Mary Marre <mmarre at ttic.edu> wrote:

>
> *When:      Wednesday, August 29th at 11:00 am  **NOTE - Unusual Day** *
>
>
>
> *Where:     *TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
>
>
> *Who:        *Gal Chechick; Bar-Ilan University/Google
>
>
>
> *Title:*        Talking about images
>
> *Abstract:*
> Learning to understand and describe complex visual scenes raises hard
> challenges: it often requires to learn to generalize effectively from few
> samples and sometimes take into account the unseen context of an image. I
> will discuss two research thrusts for facing these challenges. First,
> modelling context, I will discuss an unsupervised approach to model
> listener expectations during communication, and an approach to describe
> images in a natural but discriminative language. Second, I will discuss
> leveraging small label sets for large-scale image understanding.
>
> Joint work with Rama Vednatam, Lior Bracha, Yuval Atzmon, Tom Duerig,
> Ariel Fuxman, Neil alldrin, Devi Parikh, Kevin Murphy and Samy Bengio.
>
>
> *Bio:*
> Gal Chechik is a staff research scientist at Google Brain, California and
> an Associate  Professor at the Gonda Brain research institute in Bar-Ilan
> U. Israel. His research spans learning in brains and machines, including
> large-scale learning algorithms for machine perception, and analysis of
> representation and development of mammalian brains.  Gal earned his PhD
> from the Hebrew University in Jerusalem, followed by a postdoctoral
> research at Stanford. He is the author ~75 papers and ~35 patents,
> including publications in Nature Biotech, Cell, and PNAS.
>
>
> Host:  Greg Shakhnarovich <greg at ttic.edu>
>
>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 523*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20180828/f04621c0/attachment-0001.html>


More information about the Colloquium mailing list