Deep Generative Modeling

This course on Deep Generative Modeling aims to teach students the following: - Understanding the difference between supervised and unsupervised learning - Learning about generative modeling and its goals - Exploring the concept of latent variables and their importance - Studying autoencoders and their role in representation learning - Diving into Variational Autoencoders (VAEs) and their optimization - Gaining insights into Generative Adversarial Networks (GANs) and their applications - Discovering the use of GANs for image synthesis and distribution transformations The course teaches skills such as: - Building generative models - Implementing autoencoders and VAEs - Understanding GANs and their training process The teaching method involves lectures, slides, and lab materials, with a focus on theoretical concepts and practical applications in deep generative modeling. This course is intended for individuals interested in deep learning, specifically those looking to explore generative modeling techniques and their applications in various domains.