Generative Models🔗
In this class, we cover three types of generative models: Variational Autoencoders, Generative Adversarial Networks, and Score-based models (also called diffusion models).
Score-based models, Colab version
Additional Resources🔗
- Intuitively Understanding Variational Autoencoders
- Understanding Variational Autoencoders (VAEs)
- The deep learning book is fully available online and contains many great examples. Notebook versions of those examples are available here. Chapter 20 covers generative models and section 20.10.4 specifically covers GANs.
- Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. "Score-Based Generative Modeling through Stochastic Differential Equations." International Conference on Learning Representations, 2021.
- Jonathan Ho, Ajay Jain, and Pieter Abbeel. "Denoising diffusion probabilistic models." Advances in Neural Information Processing Systems. 2020.
- Yang Song, and Stefano Ermon. "Generative modeling by estimating gradients of the data distribution." Advances in Neural Information Processing Systems. 2019.