Instructor: Yifan Peng ([email protected])
Time: Jan. 27, 2025 - April 7, 2025, 3:30-4:45 pm East Time on Mondays
Grading: Letter grade
The emergence of ChatGPT and other large language models (LLMs) has the potential to revolutionize research and clinical practice. This course provides students with an understanding of Generative AI, using ChatGPT and other LLMs as examples, and its applications in health. Students will acquire knowledge of natural language processing, generative AI, large language models, and the range of prompting methods available for processing clinical text. Hands-on experience and a toolkit will provide useful skills for managing text data to solve a variety of problems in the health domain.
The course follows the progression of topics: an introduction to NLP, NLP tasks in healthcare, LLMs, prompt engineering, LLM training/fine-tuning, knowledge and reasoning, LLM agent, and LLM applications in healthcare. Each topic is addressed in a module lasting 1-2 weeks. Students will work on individual assignments alongside these activities, as well as participate in a team project.
- Basic Probability and Statistics: You should know the basics of probabilities, mean, standard deviation, etc.
The following texts are useful, but none are required.
- Peter Lee, Carey Goldberg, Issac Kohane, The AI Revolution in Medicine: GPT-4 and Beyond, Pearson, 2023.
| Week | Topic 1 | Event | Deadline |
|---|---|---|---|
| 1/27 | Course overview | Final project | |
| 2/3 | Introduction to NLP | ||
| 2/10 | Large Language Model | Assignment 1 | Team members decided |
| 2/17 | No classes | ||
| 2/24 | Prompt engineering | ||
| 3/3 | Training/fine-tuning | Assignment 2 | Assignment 1 |
| 3/10 | Knowledge and reasoning | Final project proposal | |
| 3/17 | LLM agent | ||
| 3/24 | Multimodal foundation model | Assignment 2 | |
| 3/31 | LLM in healthcare | ||
| 4/7 | Final project presentation | ||
| 4/14 | Final project |