COSC 742 Large Language Models for Computing and Engineering
This course provides an in-depth exploration of large language models (LLMs).
It covers foundational concepts of data pre-processing and model
architecture, including transformer attention mechanisms. The course
discusses advanced techniques for pre-training and fine-tuning, such as low rank adaptation (LoRA) and reinforcement learning from human feedback
(RLHF). Further, it examines practical applications of LLMs in computing and
engineering, such as semantic search, and it addresses pivotal research topics
pertinent to advancing the technology, such as model explainability and
model alignment. The curriculum includes discussions on the ethical
considerations and societal impact of AI, emphasizing responsible
development with topics such as model transparency and bias mitigation.
This course balances theory and practice, equipping students with the
knowledge and skills needed to excel in research and industry.
Offered
Fall