Course Websites

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: 1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.

Description: This course introduces modern machine learning techniques for developing and deploying generative models across a range of data modalities. Topics include autoregressive models for text and image generation, such as transformers and GPT-style architectures, with sampling carried out sequentially from conditional distributions. The course also covers image generation approaches including variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, energy-based models, and normalizing flows. Emphasis is placed on model architecture design, training objectives (such as maximum likelihood estimation, adversarial losses, and denoising losses), and inference methods including autoregressive sampling, Langevin dynamics, and Markov chain Monte Carlo (MCMC). Additional topics include multimodal generation, representation learning, foundation model pre-training and post-training, evaluation techniques, safety considerations, and real-world applications.