Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore the probabilistic foundations and learning algorithms for deep generative models through this comprehensive Stanford University course taught by Professor Stefano Ermon. Master the theoretical underpinnings and practical implementations of variational autoencoders (VAEs), generative adversarial networks (GANs), autoregressive models, normalizing flow models, energy-based models, and score-based diffusion models across 18 detailed lectures. Begin with fundamental concepts and background knowledge before progressing through maximum likelihood learning principles and diving deep into each major generative modeling paradigm. Examine how these models parameterize complex, high-dimensional data including images, text, and speech using deep neural networks combined with advanced stochastic optimization methods. Learn evaluation techniques for generative models and discover practical applications across computer vision, natural language processing, speech processing, graph mining, reinforcement learning, reliable machine learning, and inverse problem solving. Gain hands-on experience with discrete latent variable models and cutting-edge diffusion models for both continuous and discrete data, preparing you to implement and research state-of-the-art generative AI systems.
