Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

banner-img

Course Skill Level:

Intermediate to Advanced

Course Duration:

3 day/s

  • Course Delivery Format:

    Live, instructor-led.

  • Course Category:

    AI / Machine Learning

  • Course Code:

    GANS00L21E09

Who should attend & recommended skills:

Those with intermediate Python and basic Linux & deep learning skills seeking to add GANs

Who should attend & recommended skills

  • This course is geared for those who want to create simple generator and discriminator networks that are the foundation of GAN architecture to produce photo-realistic faces and other media objects. With the potential to produce stunningly realistic animations or shocking deep fakes, GANs are a huge step forward in deep learning systems.
  • Skill-level: Foundation-level GANs for Intermediate skilled team members. This is not a basic class.
  • Python skills: Intermediate (3-5 years’ experience)
  • Deep learning-based image processing: Basic (1-2 years’ experience)
  • Basic Linux, including familiarity with command-line options such as ls, cd, cp, and su

About this course

GANs teaches you to build and train your own Generative Adversarial Networks. You will start by creating simple generator and discriminator networks that are the foundation of GAN architecture. Then, following numerous hands-on examples, you will train GANs to generate high-resolution images, image-to-image translation, and targeted data generation. Along the way, you will find pro tips for making your system smart, effective, and fast.

Skills acquired & topics covered

  • Working in a hands-on learning environment, led by our GAN expert instructor, students will learn about and explore:
  • Incredible AI technology capable of creating images, sound, and videos that are indistinguishable from the real thing. By pitting two neural networks against each other – one to generate fakes and one to spot them – GANs rapidly learn to produce photo-realistic faces and other media objects.
  • Potential to produce stunningly realistic animations or shocking deep fakes, GANs are a huge step forward in deep learning systems.
  • Building your first GAN
  • Handling the progressive growing of GANs
  • Practical applications of GANs
  • Troubleshooting your system

Course breakdown / modules

  • What are Generative Adversarial Networks?
  • How do GANs work?
  • GANs
  • Why study GANs?

  • Introduction to generative modeling
  • How do autoencoders function on a high level?
  • What are autoencoders to GANs?
  • What is an autoencoder made of?
  • Usage of autoencoders
  • Unsupervised learning
  • Code is life
  • Why did we try a GAN?

  • Foundations of GANs: Adversarial training
  • The Generator and the Discriminator
  • GAN training algorithm
  • Tutorial: Generating handwritten digits

  • Convolutional neural networks
  • Brief history of the DCGAN
  • Batch normalization
  • normalization
  • 4.4. Tutorial: Generating handwritten digits with DCGAN

  • Evaluation
  • Training challenges
  • Summary of game setups
  • Training hacks

  • Latent space interpolation
  • They grow up so fast
  • normalization in the generator
  • Summary of key innovations
  • TensorFlow Hub and hands-on
  • Practical applications

  • Introducing the Semi-Supervised GAN
  • Tutorial: Implementing a Semi-Supervised GAN
  • Comparison to a fully supervised classifier

  • Motivation
  • What is Conditional GAN?
  • Tutorial: Implementing a Conditional GAN

  • Image-to-image translation
  • Cycle-consistency loss: There and back again
  • Adversarial loss
  • Identity loss
  • Architecture
  • Object-oriented design of GANs
  • Tutorial: Cycle GAN
  • Expansions, augmentations, and applications

  • Context of adversarial examples
  • Lies, damned lies, and distributions
  • Use and abuse of training
  • Signal and the noise
  • Not all hope is lost
  • Adversaries to GANs

  • GANs in medicine
  • GANs in fashion

  • Ethics
  • GAN innovations
  • Further reading
  • Looking back and closing thoughts