Explore Bayesian inference in generative models through this comprehensive 50-minute tutorial by Luke Hewitt from MIT. Delve into various approximate inference methods, including sampling-based techniques like MCMC and particle filters, as well as variational inference. Learn how neural networks can enhance these methods and discover the power of probabilistic programming languages for black-box Bayesian inference in complex models. Engage in hands-on exercises to implement inference algorithms for simple models and explore complex models using probabilistic programming languages. Access additional resources, including slides, references, and exercises, to further enhance your understanding of topics such as exact inference, Monte Carlo methods, gradient descent, normalizing flows, and more.