Introduction to Machine Learning for ID Modeling
Meeting Times:
- Monday, July 29, 8:30 AM – 5:00 PM
- Tuesday July 30, 8:30 AM – 5:00 PM
- Wednesday July 31, 8:30 AM – 12:00 PM
Classroom: TBA
Module Summary:
This module introduces fundamental concepts of various machine learning methods. The course materials will focus on supervised learning and its applications in the context of infectious disease data. The module will include a combination of lectures and computer labs.
Prerequisites:
This module assumes basic knowledge in matrix algebra and probability theory. Students are also expected to have a working knowledge of the R and Python computing environment.
Module Content:
- Gradient Descent
- Statistical Learning Theory
- Cross-validation Methods
- Regularization and Shrinkage Methods
- Introduction to Basic Artificial Neural Networks
- Introduction to Advanced Artificial Neural Networks (e.g., RNN, CNN, GNN)
Instructors
Max Lau, PhD
Assistant Professor, Biostatistics, Emory University
Dr. Lau's research focuses on developing novel modeling techniques for infectious disease data. His work has been successfully applied to understand transmission dynamics and controls of diseases such as measles, influenza, Ebola, and SARS-CoV-2. At Emory, he designs and teaches graduate-level machine learning and modeling classes.
Wei Jin, PhD
Assistant Professor, Computer Science, Emory University
Dr. Jin’s research is dedicated to advancing machine learning models specifically tailored for graph data, a common data structure in the study of infectious diseases. He has rich experience in developing neural network models, and his work has been successfully applied in various domains, such as single-cell analysis, traffic management, and e-commerce. At Emory, he designs and teaches undergraduate- and graduate-level machine learning and modeling classes.
Required Software:
- R
- Python
Recommended Reading:
- An introduction to statistical learning with Applications in R (Gareth James et al, Springer)
- The elements of statistical learning (Trevor Hastie et al, Springer)
- Deep Learning on Graphs (Yao Ma and Jiliang Tang, Cambridge University Press) (Chapters 2, 3, 5)
