[Colloquium] REMINDER: 2/20 Talks at TTIC: Fisher Yu, UC Berkeley

[Mary Marre via Colloquium]

When:     Wednesday, February 20th at *11:00 am*

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

Who:       Fisher Yu, UC Berkeley*T**itle:       *Towards Human-Level
Recognition via Contextual, Dynamic, and Predictive Representations
*Abstract:*
Existing state-of-the-art computer vision models usually specialize in
single domains or tasks. This specialization isolates different vision
tasks and hinders deployment of robust and effective vision systems.  In
this talk, I will discuss unified image representations suitable for
different scales and tasks through the lens of pixel-level prediction.
These connections, built by the study of dilated convolutions and deep
layer aggregation, can interpret convolutional network behaviors and lead
to model frameworks applicable to a wide range of tasks. Beyond scales and
tasks, I will argue that a unified representation should also be dynamic
and predictive. I will illustrate the case with input-dependent dynamic
networks, which lead to new insights into the relationship of
zero-shot/few-shot learning and network pruning, and with semantic
predictive control, which utilizes prediction for better driving policy
learning. To conclude, I will discuss on-going system and algorithm
investigations which couple representation learning and real-world
interaction to build intelligent agents that can continuously learn from
and interact with the world.



*Host:* Greg Shakhnarovich <greg at ttic.edu>





Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Tue, Feb 19, 2019 at 3:31 PM Mary Marre <mmarre at ttic.edu> wrote:

> When:     Wednesday, February 20th at *11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Fisher Yu, UC Berkeley*T**itle:       *Towards Human-Level
> Recognition via Contextual, Dynamic, and Predictive Representations
> *Abstract:*
> Existing state-of-the-art computer vision models usually specialize in
> single domains or tasks. This specialization isolates different vision
> tasks and hinders deployment of robust and effective vision systems.  In
> this talk, I will discuss unified image representations suitable for
> different scales and tasks through the lens of pixel-level prediction.
> These connections, built by the study of dilated convolutions and deep
> layer aggregation, can interpret convolutional network behaviors and lead
> to model frameworks applicable to a wide range of tasks. Beyond scales and
> tasks, I will argue that a unified representation should also be dynamic
> and predictive. I will illustrate the case with input-dependent dynamic
> networks, which lead to new insights into the relationship of
> zero-shot/few-shot learning and network pruning, and with semantic
> predictive control, which utilizes prediction for better driving policy
> learning. To conclude, I will discuss on-going system and algorithm
> investigations which couple representation learning and real-world
> interaction to build intelligent agents that can continuously learn from
> and interact with the world.
>
>
>
> *Host:* Greg Shakhnarovich <greg at ttic.edu>
>
>
>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Thu, Feb 14, 2019 at 3:51 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> When:     Wednesday, February 20th at *11:00 am*
>>
>> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:       Fisher Yu, UC Berkeley*T**itle:       *Unified Image
>> Representations for Semantic, Geometric, and Motion Perception
>> *Abstract:*
>> Existing state-of-the-art computer vision models usually specialize in
>> single domains or tasks. This specialization isolates different vision
>> tasks and hinders deployment of robust and effective vision systems.  In
>> this talk, I will discuss unified image representations suitable for
>> different scales and tasks through the lens of pixel-level prediction.
>> These connections, built by the study of dilated convolutions and deep
>> layer aggregation, can interpret convolutional network behaviors and lead
>> to model frameworks applicable to a wide range of tasks. Beyond scales and
>> tasks, I will argue that a unified representation should also be dynamic
>> and predictive. I will illustrate the case with input-dependent dynamic
>> networks, which lead to new insights into the relationship of
>> zero-shot/few-shot learning and network pruning, and with semantic
>> predictive control, which utilizes prediction for better driving policy
>> learning. To conclude, I will discuss on-going system and algorithm
>> investigations which couple representation learning and real-world
>> interaction to build intelligent agents that can continuously learn from
>> and interact with the world.
>>
>> *Host:* Greg Shakhnarovich <greg at ttic.edu>
>>
>>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *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/20190220/eff868d2/attachment-0001.html>