[Lisa_seminaires] [mila-tous] [Tea Talk] Yaroslav Ganin (MILA) Fri June 15 10:30AM AA3195

xavier bouthillier xavier.bouthillier at gmail.com
Jeu 14 Juin 09:57:10 EDT 2018


Small note, due to the transition to lab-organisation accounts on BlueJeans
the new link for streaming is this one
https://mila.bluejeans.com/1365483656/webrtc

On Tue, Jun 12, 2018 at 1:35 PM, Michael Noukhovitch <mnoukhov at gmail.com>
wrote:

> This week we have our very own Yaroslav Ganin giving a talk on the work he
> did on internship at DeepMind on Friday June 15th at 10:30AM in room AA3195
>
> This talk may be streamed as usual here
> <https://bluejeans.com/809027115/webrtc>
> And you can sign up to meet the speaker by messaging him on slack
>
> If you don't come to the talk, be prepared for a strongly reinforced
> adversary in the form of me!
> Michael
>
> *TITLE* Synthesizing Programs for Images using Reinforced Adversarial
> Learning
>
> *KEYWORDS *GAN, Reinforcement Learning, Unsupervised Learning
>
> *ABSTRACT *
> Advances in deep generative networks have led to impressive results in
> recent years. Nevertheless, such models can often waste their capacity on
> the minutiae of datasets, presumably due to weak inductive biases in their
> decoders. This is where graphics engines may come in handy since they
> abstract away low-level details and represent images as high-level
> programs. Current methods that combine deep learning and renderers are
> limited by hand-crafted likelihood or distance functions, a need for large
> amounts of supervision, or difficulties in scaling their inference
> algorithms to richer datasets. To mitigate these issues, we present SPIRAL,
> an adversarially trained agent that generates a program which is executed
> by a graphics engine to interpret and sample images. The goal of this agent
> is to fool a discriminator network that distinguishes between real and
> rendered data, trained with a distributed reinforcement learning setup
> without any supervision. A surprising finding is that using the
> discriminator’s output as a reward signal is the key to allow the agent to
> make meaningful progress at matching the desired output rendering. To the
> best of our knowledge, this is the first demonstration of an end-to-end,
> unsupervised and adversarial inverse graphics agent on challenging real
> world (MNIST, Omniglot, CelebA) and synthetic 3D datasets
>
> --
> You received this message because you are subscribed to the Google Groups
> "MILA Tous" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to mila-tous+unsubscribe at mila.quebec.
>
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20180614/5e42a328/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires