یان لیکان در این سخنرانی
شبکه های رقابتی مولد
یا
Generative Adversarial Networks
را مهم ترین ایده در 20 سال گذشته برای یادگیری ماشین بیان کرده است.

روشی که مدلها را قادر به یادگیری بدون ناظر می‌کند.

The major advancements in Deep Learning in 2016
🔗https://tryolabs.com/blog/2016/12/06/major-advancements-deep-learning-2016/

Generative Adversarial Nets
https://arxiv.org/pdf/1406.2661v1.pdf

این روش برای مسائل با تعداد کم و ناکافی داده ی با برچسب نیز مناسب است.
#autoencoder #unsupervised #unsupervised_learning #Generative #Generative_Models

مقاله‌ی جالب کمپانی اپل!
( Submitted for review to a conference on Nov 15, 2016)

✏️Title:
Learning from Simulated and Unsupervised Images through Adversarial Training

✏️abstract:
With recent progress in graphics, it has become more tractable to train models on #synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. To reduce this gap, we propose Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using #unlabeled real data, while preserving the annotation information from the simulator. We develop a method for S+U learning that uses an #adversarial network similar to #Generative Adversarial Networks (#GANs), but with synthetic images as inputs instead of random vectors. We make several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts and stabilize training: (i) a 'self-regularization' term, (ii) a local adversarial loss, and (iii) updating the discriminator using a history of refined images. We show that this enables generation of highly realistic images, which we demonstrate both qualitatively and with a user study. We quantitatively evaluate the generated images by training models for gaze estimation and hand pose estimation. We show a significant improvement over using synthetic images, and achieve state-of-the-art results on the MPIIGaze dataset without any labeled real data.

🔗https://arxiv.org/abs/1612.07828v1
🔗https://arxiv.org/pdf/1612.07828v1.pdf

#unlabeled_data #unsupervised #unsupervised_learning #Generative #Generative_Models

Deep Learning 2016: The Year in Review

http://www.deeplearningweekly.com/blog/deep-learning-2016-the-year-in-review

✔️ #Unsupervised and #Reinforcement Learning
✔️ Deep Reinforcement Learning
✔️ #Generative Models
✔️ Continued Openness in AI development
✔️ Partnerships & Acquisitions
✔️ Hardware & Chips

(by Jan Bussieck on December 31, 2016)

In order to understand trends in the field, I find it helpful to think of developments in #deep_learning as being driven by three major frontiers that limit the success of #artificial_intelligence in general and deep learning in particular. Firstly, there is the available #computing power and #infrastructure, such as fast #GPUs, cloud services providers (have you checked out Amazon's new #EC2 P2 instance ?) and tools (#Tensorflow, #Torch, #Keras etc), secondly, there is the amount and quality of the training data and thirdly, the algorithms (#CNN, #LSTM, #SGD) using the training data and running on the hardware. Invariably behind every new development or advancement, lies an expansion of one of these frontiers.
...

Generative Adversarial Denoising Autoencoder for #Face Completion
pic: http://www.cc.gatech.edu/~hays/7476/projects/Avery_Wenchen/images/one.png

🔗http://www.cc.gatech.edu/~hays/7476/projects/Avery_Wenchen/
#GAN
#Generative #adversarial #Generative_Models #Autoencoder

#مقاله
✔️ایجاد یک نگاشت از تصور به تصویر:
در این کار شبکه های شرطی در مقابل حریف (GAN) آموزش دیده اند که یک نگاشت از تصویر ورودی به تصویر خروجی بیابند...


Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
[UC Berkeley] pic: http://bit.ly/2s2OTsm

🔗abstract:
https://arxiv.org/abs/1703.10593

🔗Paper:
https://arxiv.org/pdf/1703.10593.pdf

🔗Project Page:
https://junyanz.github.io/CycleGAN/

🔗codes:
https://github.com/junyanz/CycleGAN
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix


Our goal is to learn a mapping G: X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.

مرتیط به مقاله ی:
https://t.me/cvision/171

#CycleGAN #GAN #Generative #CNN #Convolutional #deep_learning #adversarial #Generative_Models #Generative

#آموزش در سایت ماکروسافت
Learning Image to Image Translation with CycleGANs
[Published June 12, 2017]
https://www.microsoft.com/reallifecode/2017/06/12/learning-image-image-translation-cyclegans/

مرتبط با https://t.me/cvision/214

#CycleGAN #GAN #Generative #CNN #Convolutional #deep_learning #adversarial #Generative_Models #Generative