Generative Adversarial Networks (GANs) are one of the most popular Machine Learning algorithms developed in recent times. Since the inception of GAN in 2014, there has been a surge in interest for research on GAN and along with that generative models had started showing promising results. GANs have been used in real-life applications for text/image/video generation, drug discovery and text-to-image synthesis.
Amid the popularity of GANs, it’s extremely difficult to understand the underlying math and how does the objective function converge. In this hack session, we will talk about how GAN can be leveraged to generate a synthetic image given a textual demonstration about the image. The session will have tutorials on how to build a text-to-image model from scratch.
- End to end understanding of GANs
- Implement GANs from scratch
- Understand how to use Adversarial training to solve Domain gap alignment
- Formulate business use-cases using adversarial training
Check out the video below to know more about the session.