Learn how to build and train generative adversarial networks (GANs) using dense neural networks in this interactive, workshop-style coding course.
Overview
Syllabus
Introduction
- Understanding generative modeling
- Course outline and prerequisites
- Set up the virtual environment and run the notebook server
- Introducing generative adversarial networks (GANs)
- Instantiating the dataset and data loader
- Viewing training data
- Big picture overview of a GAN
- Training the adversaries
- The generator architecture and discriminator architecture
- Understanding the generator and discriminator outputs
- Stand-alone training of discriminator as classification model
- Stand-alone training of generator
- Computing losses for generator and discriminator
- Understanding the minimax loss function
- Setting up GAN training
- Visualizing GAN training results
- Problems with GANs and potential mitigations
- Summary and next steps
Taught by
Janani Ravi