GANs
A class of AI algorithms used in generative modeling. Jeremy Howard mentions fast.ai has achieved GAN-level outcomes without needing GANs and with transfer learning on a single GPU.
Build a research pod on GANs.
6 expert discussions. Save them all to your own pod, ask any question, get cited answers.
Common Themes
Videos Mentioning GANs
Jeremy Howard: fast.ai Deep Learning Courses and Research | Lex Fridman Podcast #35
Lex Fridman
A class of AI algorithms used in generative modeling. Jeremy Howard mentions fast.ai has achieved GAN-level outcomes without needing GANs and with transfer learning on a single GPU.
MIT 6.S094: Deep Learning
Lex Fridman
Generative Adversarial Networks, discussed for their use in generating photorealistic images, including for training autonomous vehicles.
Stanford CS153 Frontier Systems | Amit Jain from Luma AI on Unified Intelligence Systems
Stanford Online
Generative Adversarial Networks, a technique used for a time but considered finicky; still useful for distillation and real-time systems but less scalable than transformers.
Stanford CS230 | Autumn 2025 | Lecture 8: Agents, Prompts, and RAG
Stanford Online
Generative Adversarial Networks, mentioned in the context of distribution shifts between training data and real-world data.
Stanford CS229 Machine Learning | Spring 2026 | Lecture 5: Gaussian Discriminant Analysis
Stanford Online
Discussed as generative and discriminative models popular around 2016, still valuable and cool.
Why We Made Jev — Diogo Almeida, TypeSafe Co-founder & CEO
Latent Space
Models that mode drop, dropping minority classes to focus on common ones, mentioned in contrast to older models that made blurry images.