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
Afficher les réponses par date
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@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@mila.quebec.
Reminder, this is in 30 minutes!
On Thu, Jun 14, 2018, 09:57 xavier bouthillier xavier.bouthillier@gmail.com wrote:
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@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@mila.quebec.
-- 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@mila.quebec.
Here is the recording
https://bluejeans.com/s/jy5Rl/
And the slides
https://docs.google.com/presentation/d/1ZWFDcuJqQI4HmrkwtBPzV16WNr2Lq7Xf2mPq...
On Fri, Jun 15, 2018 at 9:59 AM, Michael Noukhovitch mnoukhov@gmail.com wrote:
Reminder, this is in 30 minutes!
On Thu, Jun 14, 2018, 09:57 xavier bouthillier < xavier.bouthillier@gmail.com> wrote:
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@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@mila.quebec.
-- 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@mila.quebec.
-- 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@mila.quebec.
lisa_seminaires@iro.umontreal.ca
-
Michael Noukhovitch -
xavier bouthillier