This course is now FULL, and you can join the waitlist. In the case that a spot becomes available, an SCPD student representative will contact you. Make sure you have submitted your NDO application and required documents to be considered.

Generative models are a key paradigm for probabilistic reasoning within graphical models and probabilistic programming languages. It is one of the exciting and rapidly-evolving fields of statistical machine learning and artificial intelligence. Recent advances in parameterizing generative models using deep neural networks, combined with progress in stochastic optimization methods, have enabled scalable modeling of complex, high-dimensional data including images, text, and speech. In this course, we will study the probabilistic foundations and learning algorithms for deep generative models and discuss application areas that have benefitted from deep generative models.

Topics Include

  • Autoregressive models
  • Variational autoencoders
  • Normalizing flow models
  • Generative adversarial networks
  • Energy-based models
  • Learning data distribution
  • Application of various algorithms to decision making, finding analogies, and predicting future events
  • Various applications to deep generative models including computer vision, speech and language processing