GANs are a type of deep neural network that allow us to generate data. In this webinar, we’ll take a look at the concept and theory behind GANs, which can be used to train neural nets with data that is generated by the network. We’ll explore the GAN framework along with its components -- generator and discriminator networks. We’ll then learn how to use Apache MXNet on AWS using the popular MNIST dataset, which contains images of handwritten numbers. In the end, we’ll create a GAN model that is able to generate similar images of handwritten numbers from our test dataset.
2. |Webinars
• Intro to AI and Deep Learning
• Intro to GANs (Generative Adversarial Networks)
• GAN Research & Applications
• GAN Implementation & Demo
Agenda
3. |Webinars
Tons of GPUs and CPUs
Serverless
At the Edge, On IoT Devices
Prediction
The Challenge For Artificial Intelligence: SCALE
Tons of GPUs
Elastic capacity
Training
Pre-built images
Aggressive migration
New data created on AWS
Data
PBs of existing data
7. |Webinars
Deep Neural Network
hidden layers
The optimal size of the hidden
layer (number of neurons) is
usually between the size of the
input and size of the output layers
Input layer
output
8. |Webinars
The “Learning” in Deep Learning
0.4 0.3
0.2 0.9
...
back propogation (gradient descent)
X1 != X
0.4 ± 𝛿 0.3 ± 𝛿
new
weights
new
weights
0
1
0
1
1
.
.
-
-
X
input
label
...
X1
11. |Webinars
GAN (Generative Adversarial Networks)
Input:
Noise
Generator
Generated
(“Fake”)
Data
Data From
Dataset
(“Real”)
Discriminator
Real or
Fake?
Framework for creating generative models
14. |Webinars
SRGAN: Making Images High Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (Ledig et. al 2016 )
15. |Webinars
StackGAN: Create Images from Text
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks (Zhang et. al 2016)
16. |Webinars
3D-GAN: 3D Models from Images
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (Wu et al 2017)
17. |Webinars
CycleGAN: Image to Image Translation
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (Zhu et al 2017)
18. |Webinars
DiscoGAN: Discover Relationships Between Images
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (Kim et al 2017)
Gender conversion
Hair color conversion