Practical AI Making GANs practical
Dec 2, 2019
Jakub Langr and Vladimir Bok, authors of "GANs in Action" and experts on Generative Adversarial Networks, dive into the transformative world of GANs. They unpack the basics and unique training processes that set GANs apart from traditional neural networks. The discussion highlights their revolutionary applications in creating photorealistic imagery and explores innovative types like CycleGAN and StyleGAN. Additionally, they address the ethical implications of GAN technology, including the risks of deepfakes, while discussing practical entry points for newcomers.
AI Snips
Chapters
Books
Transcript
Episode notes
Langr's GAN Journey
- Jakub Langr became fascinated with GANs shortly after Ian Goodfellow's 2014 paper.
- His interest grew from blog posts to a full-time GANs career, including co-authoring "GANs in Action."
Bok's GAN Experience
- Vlad Bok encountered GANs during a research project at Microsoft Research.
- He observed GANs' step-wise improvement in data generation over previous state-of-the-art methods.
GANs' Core Idea
- GANs utilize two competing neural networks: a generator and a discriminator.
- This unsupervised approach lets GANs learn from raw data, like images, to create new, similar data.
