AI Engineering and Applications. 3 credits, 3 contact hours

Catalog description

This graduate course introduces machine learning (ML) from a systems and applications perspective, emphasizing the hardware and computational frameworks that enable modern AI in engineering domains. Students examine high-performance computing, distributed training, and hardware accelerators (e.g., GPUs and specialized AI architectures) that support scalable ML, alongside case studies in robotics, autonomous systems, materials design, and healthcare. The course also covers state-of-the-art methods, including transformers, attention mechanisms, generative models (GANs and diffusion), natural language processing with large language models, prompt engineering, parameter-efficient fine-tuning (e.g., LoRA), retrieval-augmented generation, knowledge distillation, and reinforcement learning with human feedback. Building on this applications-driven foundation, the course introduces core ML principles, including multivariate statistical analysis and classical techniques such as regression, classification, clustering, and support vector machines, along with essential optimization methods and an overview of deep learning architectures. Students are expected to know basic concepts of machine learning before taking this course.