09.05.2023 Views

pdfcoffee

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Generative

Adversarial Networks

In this chapter we will discuss Generative Adversarial Networks (GANs) and

its variants. GANs have been defined as the most interesting idea in the last 10 years

in ML (https://www.quora.com/What-are-some-recent-and-potentiallyupcoming-breakthroughs-in-deep-learning)

by Yann LeCun, one of the fathers

of deep learning. GANs are able to learn how to reproduce synthetic data that looks

real. For instance, computers can learn how to paint and create realistic images.

The idea was originally proposed by Ian Goodfellow (for more information refer to

NIPS 2016 Tutorial: Generative Adversarial Networks, by I. Goodfellow, 2016); he has

worked with the University of Montreal, Google Brain, and OpenAI, and is presently

working in Apple Inc as the Director of Machine Learning.

In this chapter we will cover different types of GANs and see some of their

implementation in TensorFlow 2.0. Broadly we will cover the following topics:

• What is a GAN?

• Deep convolutional GANs

• SRGAN

• CycleGAN

• Applications of GANs

What is a GAN?

The ability of GANs to learn high-dimensional, complex data distributions have

made them very popular with researchers in recent years. Between 2016, when

they were first proposed by Ian Goodfellow, up to 2019, we have more than 40,000

research papers related to GANs. This is in the space of just three years!

[ 191 ]

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!